[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"portal-settings:figure:zh":3,"public-menus:all":45,"post:nvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform:zh":531,"related:post:nvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform:zh:1":994},{"statusCode":4,"data":5,"message":44},200,{"tenantId":6,"lang":7,"defaultLang":8,"siteUrl":9,"contactEmail":10,"brandName":11,"logoUrl":12,"siteName":11,"siteDescription":13,"ogImage":14,"robotsIndex":15,"socialLinks":14,"reservedSlugs":14,"seoPolicy":16},"figure","zh","en","https:\u002F\u002Ffigure.rocks","info@stajic.de","Figure Rocks","\u002Ffavicon-32x32.png","",null,true,{"branding":17,"relatedContent":18,"crossDomainLinks":19},{"logoUrl":12},{"enabled":15},[20,23,26,29,32,35,38,41],{"url":21,"label":22,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002Floving.rocks","loving.rocks",{"url":24,"label":25,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002Fstajic.de","stajic.de",{"url":27,"label":28,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002Fbazify.com","bazify.com",{"url":30,"label":31,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002Fbazify.de","bazify.de",{"url":33,"label":34,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002F2mesta.com","2mesta.com",{"url":36,"label":37,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002F2mesta.de","2mesta.de",{"url":39,"label":40,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002Fbazify.at","bazify.at",{"url":42,"label":43,"isActive":15,"showInFooter":15,"includeInSameAs":15},"https:\u002F\u002Fweb-hoch3.de","web-hoch3.de","Portal settings resolved",[46],{"id":47,"name":48,"location":49,"isActive":15,"isDefault":15,"items":50},2,"Main Menu","sidebar",[51,65,189,282,358,424],{"id":52,"title":53,"url":61,"target":62,"icon":63,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":64},"1",{"de":54,"en":55,"es":56,"fr":57,"it":55,"ru":58,"sr":59,"zh":60},"Startseite","Home","Inicio","Accueil","Главная","Početna","首页","\u002F","_self","i-lucide-home",[],{"id":66,"title":67,"url":76,"target":62,"icon":77,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":78},"3",{"de":68,"en":69,"es":70,"fr":71,"it":72,"ru":73,"sr":74,"zh":75},"Spiele","Games","Juegos","Jeux","Giochi","Игры","Igre","游戏","\u002Fgames","i-lucide-gamepad-2",[79,92,107,121,135,148,162,176],{"id":80,"title":81,"url":76,"target":62,"icon":90,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":91},"3-1",{"de":82,"en":83,"es":84,"fr":85,"it":86,"ru":87,"sr":88,"zh":89},"Spiele-Hub","Games Hub","Centro de juegos","Hub de jeux","Hub Giochi","Игровой центр","Centar za igre","游戏中心","i-lucide-layout-grid",[],{"id":93,"title":94,"url":103,"target":62,"icon":104,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":106},"1-1",{"de":95,"en":96,"es":97,"fr":98,"it":99,"ru":100,"sr":101,"zh":102},"Neu & Angesagt","New & Trending","Novedades & Tendencias","Nouveautés & Tendances","Novità & Tendenze","Новинки & тренды","Novo & Popularno","新品 & 热门","\u002Fnews\u002Fgaming-news","i-lucide-sparkles","custom",[],{"id":108,"title":109,"url":118,"target":62,"icon":119,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":120},"1-2",{"de":110,"en":111,"es":112,"fr":113,"it":114,"ru":115,"sr":116,"zh":117},"Angebote","Deals","Ofertas","Offres","Offerte","Акции","Ponude","优惠","\u002Fdeals","i-lucide-badge-percent",[],{"id":122,"title":123,"url":132,"target":62,"icon":133,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":134},"1-3",{"de":124,"en":125,"es":126,"fr":127,"it":128,"ru":129,"sr":130,"zh":131},"Release-Kalender","Release Calendar","Calendario de lanzamientos","Calendrier des sorties","Calendario delle uscite","Календарь релизов","Kalendar izdanja","发布日历","\u002Freleases","i-lucide-calendar-days",[],{"id":136,"title":137,"url":145,"target":62,"icon":146,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":147},"3-2",{"de":138,"en":139,"es":140,"fr":141,"it":142,"sr":143,"zh":144},"amiibo-kompatible Spiele","amiibo-Compatible Games","Juegos compatibles con Amiibo","Jeux compatibles Amiibo","Giochi compatibili con amiibo","Amiibo kompatibilne igre","Amiibo 兼容游戏","\u002Freference\u002Fcompatibility","i-lucide-check-circle-2",[],{"id":149,"title":150,"url":159,"target":62,"icon":160,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":161},"3-3",{"de":151,"en":152,"es":153,"fr":154,"it":155,"ru":156,"sr":157,"zh":158},"Wie amiibo funktionieren","How amiibo work","Cómo funcionan los Amiibo","Comment fonctionnent les Amiibo","Come funzionano gli Amiibo","Как работают Amiibo","Kako Amiibo rade","Amiibo 如何运作","\u002Fgames\u002Fhow-amiibo-unlocks-work","i-lucide-puzzle",[],{"id":163,"title":164,"url":173,"target":62,"icon":174,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":175},"3-4",{"de":165,"en":166,"es":167,"fr":168,"it":169,"ru":170,"sr":171,"zh":172},"Beste Amiibo pro Spiel","Best amiibo per Game","Mejores Amiibo por juego","Meilleurs Amiibo par jeu","Migliori Amiibo per gioco","Лучшие Amiibo по играм","Najbolji Amiibo po igri","各游戏最佳 Amiibo","\u002Fgames\u002Fbest-amiibo-per-game","i-lucide-award",[],{"id":177,"title":178,"url":186,"target":62,"icon":187,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":188},"3-5",{"de":179,"en":180,"es":181,"fr":182,"it":183,"ru":184,"sr":185},"Freischaltbares & Belohnungen","Unlockables & Rewards","Desbloqueables & Recompensas","Déblocables & Récompenses","Sbloccabili & Ricompense","Разблокировки & награды","Otključavanja & nagrade","\u002Fgames\u002Funlocks-and-benefits","i-lucide-gift",[],{"id":190,"title":191,"url":199,"target":62,"icon":200,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":201},"4",{"de":192,"en":193,"es":194,"it":195,"ru":196,"sr":197,"zh":198},"Sammeln","Collecting","Coleccionismo","Collezionismo","Коллекционирование","Kolekcionarstvo","收藏","\u002Fcollecting","i-lucide-gem",[202,213,227,240,254,268],{"id":203,"title":204,"url":211,"target":62,"icon":90,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":212},"4-1",{"de":205,"en":206,"fr":207,"it":208,"ru":209,"zh":210},"Sammel-Hub","Collecting Hub","Hub de collecte","Hub di raccolta","Центр сбора","收藏中心","\u002Famiibo\u002Fcollecting",[],{"id":214,"title":215,"url":224,"target":62,"icon":225,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":226},"4-2",{"de":216,"en":217,"es":218,"fr":219,"it":220,"ru":221,"sr":222,"zh":223},"Kaufberatung","Buying Guide","Guía de compra","Guide d'achat","Guida all'acquisto","Гид покупателя","Vodič za kupovinu","购买指南","\u002Famiibo-library\u002Famiibo-buying-smart","i-lucide-shopping-bag",[],{"id":228,"title":229,"url":237,"target":62,"icon":238,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":239},"4-3",{"de":230,"en":230,"es":231,"fr":232,"it":233,"ru":234,"sr":235,"zh":236},"Fake vs Real","Falso vs. Real","Faux vs Vrai","Falso vs Vero","Фейк vs Оригинал","Lažno vs Pravo","真假对比","\u002Famiibo-library\u002Famiibo-buying-smart\u002Favoid-fake-listings","i-lucide-scan",[],{"id":241,"title":242,"url":251,"target":62,"icon":252,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":253},"4-4",{"de":243,"en":244,"es":245,"fr":246,"it":247,"ru":248,"sr":249,"zh":250},"Aufbewahrung & Präsentation","Storage & Display","Almacenamiento & exhibición","Rangement & Présentation","Contenitori & Esposizione","Хранение & витрины","Odlaganje & izlaganje","存储 & 展示","\u002Famiibo-library\u002Famiibo-care-and-storage","i-lucide-box",[],{"id":255,"title":256,"url":265,"target":62,"icon":266,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":267},"4-5",{"de":257,"en":258,"es":259,"fr":260,"it":261,"ru":262,"sr":263,"zh":264},"Preisübersicht","Price Guide","Guía de precios","Guide des prix","Guida ai prezzi","Гид по ценам","Cenovnik","价格指南","\u002Fcollections\u002Fprice-guide","i-lucide-bar-chart-3",[],{"id":269,"title":270,"url":279,"target":62,"icon":280,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":281},"4-6",{"de":271,"en":272,"es":273,"fr":274,"it":275,"ru":276,"sr":277,"zh":278},"Raritäten","Rare Finds","Hallazgos únicos","Trouvailles rares","Pezzi rari","Редкие находки","Retki nalazi","稀有发现","\u002Fcollections\u002Frare-and-notable","i-lucide-trophy",[],{"id":283,"title":284,"url":292,"target":62,"icon":293,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":294},"5",{"de":285,"en":286,"es":287,"fr":286,"it":288,"ru":289,"sr":290,"zh":291},"Technik","Tech","Tecnología","Tecnologia","Технологии","Tehnologija","科技","\u002Ftech","i-lucide-cpu",[295,306,318,331,344],{"id":296,"title":297,"url":292,"target":62,"icon":90,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":305},"5-1",{"de":298,"en":298,"es":299,"fr":300,"it":301,"ru":302,"sr":303,"zh":304},"Tech Hub","Centro tecnológico","Hub Tech","Hub Tecnologico","Технохаб","Tehnološki centar","科技中心",[],{"id":307,"title":308,"url":315,"target":62,"icon":316,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":317},"5-2",{"de":309,"en":310,"fr":311,"it":312,"ru":313,"zh":314},"Audio- & Mikrofonqualität","Audio & Mic Quality","Qualité audio & micro","Qualità audio & mic","Качество звука & микрофона","音频 & 麦克风质量","\u002Fgear\u002Faudio","i-lucide-mic",[],{"id":319,"title":320,"url":328,"target":62,"icon":329,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":330},"5-3",{"de":321,"en":322,"es":323,"fr":324,"it":325,"sr":326,"zh":327},"Controller & Zubehör","Controllers & Accessories","Mandos & accesorios","Manettes & accessoires","Controller & Accessori","Kontroleri & dodatna oprema","控制器 & 配件","\u002Fgear\u002Fcontrols","i-lucide-joystick",[],{"id":332,"title":333,"url":341,"target":62,"icon":342,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":343},"5-4",{"de":334,"en":335,"es":336,"fr":337,"it":338,"ru":339,"sr":340},"Displays & Aufnahme","Displays & Capture","Pantallas & Captura","Écrans & Capture","Display & Acquisizione","Дисплеи & Захват","Ekrani & snimanje","\u002Fgear\u002Fdisplays","i-lucide-monitor",[],{"id":345,"title":346,"url":355,"target":62,"icon":356,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":357},"5-5",{"de":347,"en":348,"es":349,"fr":350,"it":351,"ru":352,"sr":353,"zh":354},"Netzwerkstabilität","Network Stability","Estabilidad de la red","Stabilité du réseau","Stabilità della rete","Стабильность сети","Stabilnost mreže","网络稳定性","\u002Fplaybooks\u002Fnetwork-stability","i-lucide-wifi",[],{"id":359,"title":360,"url":368,"target":62,"icon":369,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":370},"6",{"de":361,"en":361,"es":362,"fr":363,"it":364,"ru":365,"sr":366,"zh":367},"Shop","Tienda","Boutique","Negozio","Магазин","Prodavnica","商店","\u002Fshop","i-lucide-shopping-cart",[371,383,391,399,412],{"id":372,"title":373,"url":368,"target":62,"icon":381,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":382},"6-1",{"de":374,"en":375,"es":376,"fr":377,"ru":378,"sr":379,"zh":380},"Shop-Hub","Shop Hub","Centro de compras","Espace Boutique","Центр магазина","Centar za kupovinu","购物中心","i-lucide-store",[],{"id":384,"title":385,"url":388,"target":62,"icon":389,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":390},"6-2",{"de":386,"en":386,"es":387,"fr":387,"it":387,"sr":387,"zh":387},"amiibo","Amiibo","\u002Famiibo-shop","i-lucide-scan-line",[],{"id":392,"title":393,"url":396,"target":62,"icon":397,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":398},"6-3",{"de":394,"en":394,"es":394,"fr":394,"it":394,"ru":394,"sr":394,"zh":395},"LEGO","乐高","\u002Flego-shop","i-lucide-blocks",[],{"id":400,"title":401,"url":409,"target":62,"icon":410,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":411},"6-4",{"de":402,"en":403,"es":404,"fr":405,"it":406,"sr":407,"zh":408},"Figuren & Sammlerstücke","Figures & Collectibles","Figuras & Coleccionables","Figurines & Objets de collection","Figure & Collezionismo","Figure & kolekcionarstvo","手办 & 收藏品","\u002Fshop\u002Ffigures","i-lucide-package",[],{"id":413,"title":414,"url":421,"target":62,"icon":422,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":423},"6-5",{"de":415,"en":415,"fr":416,"it":417,"ru":418,"sr":419,"zh":420},"Gaming Gear","Équipement gaming","Accessori gaming","Игровое снаряжение","Gejming oprema","游戏装备","\u002Fgaming-gear-shop","i-lucide-headphones",[],{"id":425,"title":426,"url":427,"target":62,"icon":389,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":428},"2",{"de":386,"en":386,"es":386,"fr":386,"it":386,"ru":386,"sr":386,"zh":386},"\u002Famiibo",[429,440,447,461,475,489,503,517],{"id":430,"title":431,"url":427,"target":62,"icon":90,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":439},"2-1",{"de":432,"en":433,"es":434,"fr":435,"it":435,"ru":436,"sr":437,"zh":438},"amiibo-Hub","amiibo Hub","Centro amiibo","Hub amiibo","Хаб amiibo","amiibo centar","amiibo 中心",[],{"id":441,"title":442,"url":444,"target":62,"icon":445,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":446},"1772724791061",{"de":443,"en":443},"Franchise","\u002Famiibo\u002Ffranchise","i-lucide-star",[],{"id":448,"title":449,"url":458,"target":62,"icon":459,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":460},"2-3",{"de":450,"en":451,"es":452,"fr":453,"it":454,"ru":455,"sr":456,"zh":457},"Region & Verpackung (EU\u002FUS\u002FJP)","Region & Packaging (EU\u002FUS\u002FJP)","Región y embalaje (UE\u002FEE. UU.\u002FJP)","Région & Emballage (UE\u002FUS\u002FJP)","Regione & Confezione (EU\u002FUS\u002FJP)","Регион & упаковка (EU\u002FUS\u002FJP)","Region & pakovanje (EU\u002FUS\u002FJP)","地区 & 包装 (EU\u002FUS\u002FJP)","\u002Famiibo-library\u002Famiibo-editions-and-regions","i-lucide-globe",[],{"id":462,"title":463,"url":472,"target":62,"icon":473,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":474},"2-4",{"de":464,"en":465,"es":466,"fr":467,"it":468,"ru":469,"sr":470,"zh":471},"Schnellidentifikations-Checkliste","Fast Identification Checklist","Lista de identificación rápida","Liste d'identification rapide","Checklist identificazione rapida","Чек-лист быстрой идентификации","Kontrolna lista za brzu identifikaciju","快速识别清单","\u002Famiibo\u002Fidentify-checklist","i-lucide-list-checks",[],{"id":476,"title":477,"url":486,"target":62,"icon":487,"isActive":15,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":488},"2-6",{"de":478,"en":479,"es":480,"fr":481,"it":482,"ru":483,"sr":484,"zh":485},"Tipps für Sealed-Sammlungen","Sealed Collection Tips","Consejos de colección sellada","Conseils collection scellée","Consigli collezione sigillata","Советы по коллекции Sealed","Saveti za zapečaćene kolekcije","密封收藏贴士","\u002Famiibo\u002Fsealed-tips","i-lucide-shield-check",[],{"id":490,"title":491,"url":500,"target":62,"icon":501,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":502},"2-5",{"de":492,"en":493,"es":494,"fr":495,"it":496,"ru":497,"sr":498,"zh":499},"Zustand & Bewertung","Condition & Grading","Estado & Graduación","État & Évaluation","Condizioni & Valutazione","Состояние & Оценка","Stanje & ocenjivanje","品相与分级","\u002Famiibo-library\u002Famiibo-condition-and-grading","i-lucide-badge-check",[],{"id":504,"title":505,"url":514,"target":62,"icon":515,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":516},"2-2",{"de":506,"en":507,"es":508,"fr":509,"it":510,"ru":511,"sr":512,"zh":513},"Ausgaben & Nachdrucke","Editions & Reprints","Ediciones & Reimpresiones","Éditions & Réimpressions","Edizioni & ristampe","Издания & переиздания","Izdanja & reizdanja","版本 & 重印","\u002Famiibo\u002Fcollecting\u002F","i-lucide-layers",[],{"id":518,"title":519,"url":528,"target":62,"icon":529,"isActive":15,"type":105,"productId":14,"categoryId":14,"shopCategoryId":14,"articleId":14,"pageId":14,"portfolioId":14,"children":530},"2-7",{"de":520,"en":521,"es":522,"fr":523,"it":524,"ru":525,"sr":526,"zh":527},"Nachdruck-Timeline","Reprint Timeline","Cronología de reimpresión","Chronologie des réimpressions","Cronologia ristampe","Хронология переизданий","Hronologija reprinta","重印时间轴","\u002Freference\u002Ftimelines\u002Famiibo-reprint-timeline","i-lucide-timer",[],{"statusCode":4,"data":532,"message":993},{"id":533,"title":534,"slug":535,"content":536,"contentJson":537,"excerpt":723,"featuredImage":724,"featuredImageAlt":725,"featuredImageCaption":14,"featuredImageTitle":14,"featuredImageCopyright":14,"featuredImageAuthor":14,"featuredImageSourceUrl":14,"featuredImageLicense":14,"featuredImageIsAiGenerated":726,"status":727,"publishedAt":728,"createdAt":729,"updatedAt":730,"seoLocalePaths":731,"categories":740,"author":753,"translations":756},"459","NVIDIA RTX Spark 将 DLSS 5 和本地 AI 角色置于同一游戏平台","nvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u003Cp>2026年10月27日，NVIDIA将RTX Spark定位为不止是一个新的Windows PC平台。该公司将两种不同的AI工作负载带到同一台游戏机上：通过DLSS 5实现的神经渲染，以及通过NVIDIA ACE和Nemotron 3.5 Bolt E4B 4GB实现的本地角色智能。\u003C\u002Fp>\n\u003Cp>这种组合才是真正的新闻。游戏开始使用本地AI不仅是为了重建或生成像素，还为了解读玩家意图、对游戏状态进行推理、调用工具并驱动角色行为。技术挑战不再仅仅是模型能否运行，而是图形、语音和代理推理能否共享内存、计算和延迟预算，同时不损害游戏本身。\u003C\u002Fp>\n\u003Ch2 id=\"section-3\">直接回答\u003C\u002Fh2>\n\u003Cp>RTX Spark是NVIDIA的新Windows PC平台，用于AI开发、创作和游戏，围绕Blackwell RTX GPU和Grace CPU构建，最高支持128 GB统一内存。对于游戏，NVIDIA将该平台与DLSS 5、RTX Kit、虚幻引擎5.8支持以及新的小型语言模型Nemotron 3.5 Bolt E4B 4GB配对，专为本地AI角色设计。\u003C\u002Fp>\n\u003Cp>最重要的架构变化是神经图形和游戏代理推理正在成为并发工作负载。未来的游戏可能使用一条AI路径来改善渲染图像，而另一个模型则倾听玩家、读取相关状态、对请求进行推理并选择允许的游戏动作。\u003C\u002Fp>\n\u003Ch2 id=\"section-6\">NVIDIA在2026年10月27日宣布了什么\u003C\u002Fh2>\n\u003Cp>NVIDIA表示，RTX Spark将高达128 GB的统一内存与CUDA软件栈、光线追踪和完整的DLSS套件相结合。游戏栈还包括RTX Kit技术、Nsight开发工具、虚幻引擎5.8的RTX分支以及用于运行本地语言和语音模型的游戏内推理SDK。\u003C\u002Fp>\n\u003Cp>角色方面的更新以Nemotron 3.5 Bolt E4B 4GB为中心。NVIDIA于10月23日发布了该模型本身，四天后又强调了其在游戏中的作用。该模型可通过游戏内推理SDK提供给开发者，并针对需要在本地运行同时为应用程序其余部分保留资源的对话代理进行了优化。\u003C\u002Fp>\n\u003Cp>在渲染方面，RTX Spark支持带有3D引导神经渲染的DLSS 5，首发于NBA 2K27。NVIDIA表示，其10月DLSS 5模型更新运行速度是9月版本的两倍，GPU开销减半，在4K下使用的VRAM减少20%，同时保持相当的视觉保真度。这些是NVIDIA的测量结果，在独立测试之前应视为制造商的性能声明。\u003C\u002Fp>\n\u003Ch2 id=\"section-10\">真正的转变：游戏PC成为共享AI运行时\u003C\u002Fh2>\n\u003Cp>本地游戏AI比桌面聊天机器人面临更严格的约束：它并不拥有这台机器。游戏已经在消耗GPU时间、内存带宽、VRAM或统一内存、CPU时间、存储带宽和帧时间预算。语音识别和文本转语音可能增加另一层竞争。\u003C\u002Fp>\n\u003Cp>这使得每GB的效率比原始模型大小更重要。NVIDIA描述Nemotron 3.5 Bolt E4B在其目标工作负载中仅占用约4 GB，以便本地角色推理可以与图形和其他模型共存。因此，设计目标不仅仅是更聪明的NPC，而是一个在游戏仍在渲染时仍能保持有用的模型。\u003C\u002Fp>\n\u003Cp>这也是为什么RTX Spark作为一个平台故事而非单一模型公告很重要。神经渲染、语言推理、语音和传统游戏逻辑正在同一台机器上融合，但它们仍然有不同的时序要求和对游戏的不同权限。\u003C\u002Fp>\n\u003Ch2 id=\"section-14\">Nemotron 3.5 Bolt为本地游戏角色增加了什么\u003C\u002Fh2>\n\u003Cp>Nemotron 3.5 Bolt E4B 4GB专为对话和代理工作负载而构建，而非逐帧控制。NVIDIA将其核心能力列为自主多轮工具使用、指令遵循、可配置推理和基于游戏状态的接地。\u003C\u002Fp>\n\u003Cp>该模型支持64K上下文窗口，可容纳对话历史、指令、工具定义、检索信息和游戏状态。它还支持35种语言，而NVIDIA表示基础模型在超过140种语言上进行了预训练。\u003C\u002Fp>\n\u003Cp>NVIDIA报告称，在选定的相关基准测试中，其平均质量比上一代模型高出约40%，输出令牌比同类模型少约80%。这些数字描述的是NVIDIA的基准测试结果，并不保证NPC可信度、游戏延迟或帧节奏的改善。\u003C\u002Fp>\n\u003Cp>还有一个重要的时间线区别。PUBG的公测AI队友使用NVIDIA的第一代Nemotron小型语言模型，而Aniimo展示了第二代Nemotron模型。Nemotron 3.5 Bolt是现在宣布的新开发者模型；NVIDIA并未表示那些现有实现已经迁移到它。\u003C\u002Fp>\n\u003Cp>Figure Rocks 已在 \u003Ca href='\u002Fzh\u002Fblog\u002Fpubg-ally-shows-why-ai-teammates-need-two-brains-fast-reflexes-and-slow-reasoning'>PUBG Ally 展示了为什么 AI 队友需要两个大脑\u003C\u002Fa> 中探讨了这种分离：语言推理对于规划、协调和解释很有用，而快速战斗反应仍然属于确定性或专门的游戏侧系统。\u003C\u002Fp>\n\u003Ch2 id=\"section-20\">64K 上下文、检索、实时状态和工具不是一回事\u003C\u002Fh2>\n\u003Cp>64K 上下文窗口增加了模型一次可以考虑的信息量，但它并不会自动让角色变得知识渊博、与时俱进或正确。上下文容量回答的是可以供给多少信息。检索决定应该供给哪些外部知识。实时游戏状态描述当前会话中什么是真实的。工具定义智能体被允许检查或做什么。\u003C\u002Fp>\n\u003Cp>NVIDIA 的 ACE Game Agent SDK 直接反映了这种分离。其 Agent API 管理有状态、多步骤的工具辅助推理；其 Chat API 为开发者提供对推理的更低层级控制；其 RAG API 支持从开发者构建的数据库中进行语义、词汇和混合检索。NVIDIA 已在实验性的《全面战争：法老》顾问中展示了该检索架构，该顾问查询了超过 1,200 个相互关联的游戏数据表。\u003C\u002Fp>\n\u003Cp>对于游戏角色，这些层应保持独立。知识数据库可能说明某个物品如何运作。当前游戏状态必须说明该物品是否实际存在。模型可能判断使用该物品是合理的。一个经过验证的游戏侧函数仍必须决定该动作是否合法并执行它。\u003C\u002Fp>\n\u003Cp>本地推理也不意味着整个游戏变得离线。语言模型可能在玩家机器上运行，而多人服务器、账户系统、可下载内容或其他服务仍需要网络连接。\u003C\u002Fp>\n\u003Ch2 id=\"section-25\">DLSS 5 让同一台机器成为 AI 渲染平台\u003C\u002Fh2>\n\u003Cp>DLSS 5 引入了 3D 引导神经渲染，作为图形管线中的另一个阶段。NVIDIA 将其描述为从引擎渲染的帧中增强光照和材质细节，同时保留开发者对可更改内容的控制。现有几何体、纹理、光照缓冲区和创作场景仍是基础。\u003C\u002Fp>\n\u003Cp>这种区分很重要，因为神经渲染不是游戏引擎的替代品。它是在引擎已提供的信息上运行的推理层。同样的原则也出现在智能体一侧：语言模型可以解释和决策，但游戏引擎仍对有效状态和可执行动作拥有权威。\u003C\u002Fp>\n\u003Cp>更广泛的架构在 \u003Ca href='\u002Fzh\u002Fblog\u002Fthe-game-engine-is-becoming-part-renderer-part-scheduler-part-ai-system'>游戏引擎正变得部分渲染器、部分调度器、部分 AI 系统\u003C\u002Fa> 中进行了探讨。RTX Spark 使这种融合更加具体，因为渲染推理和智能体推理现在被设计为必须在一个本地系统上共存的工作负载。\u003C\u002Fp>\n\u003Ch2 id=\"section-29\">为什么 RTX Spark 对游戏开发者很重要\u003C\u002Fh2>\n\u003Cp>RTX Spark 不仅仅是消费级功能捆绑。NVIDIA 围绕它提供了一条开发路径：虚幻引擎 5.8 对 Windows on Arm 的支持、Nsight 性能分析工具、游戏内推理 SDK 以及八项 RTX Kit 技术，涵盖神经纹理压缩、神经着色器、几何体、降噪、角色渲染和全局光照等领域。\u003C\u002Fp>\n\u003Cp>实际意义在于，开发者可以越来越多地将图形和本地 AI 作为同一运行时预算的一部分进行分析，而不是将 AI 视为具有单独延迟和成本假设的远程服务。这创造了新的可能性，但也使调度、内存压力和最坏情况下的帧时间行为变得更加重要。\u003C\u002Fp>\n\u003Ch2 id=\"section-32\">玩家目前不应假设什么\u003C\u002Fh2>\n\u003Cp>支持 RTX Spark 并不意味着每款游戏都会突然包含非脚本化的 AI 角色。开发者仍需设计角色、暴露安全的观察和动作、集成语音或文本交互、定义记忆行为，并决定模型推理何时值得运行时成本。\u003C\u002Fp>\n\u003Cp>DLSS 5 的性能声明也不能证明每款受支持的游戏都会感觉更响应。更高的显示帧率、生成的帧、神经重建质量和输入延迟是相关但独立的测量指标。图形功能可以改善视觉流畅度，而不会降低端到端延迟的每个组成部分。\u003C\u002Fp>\n\u003Cp>同样，更强大的本地语言模型并不会使游戏行为变得确定性。开放式对话和推理可以提高适应性，但对于正确响应已知的行为，脚本化系统仍然更容易测试且更可预测。\u003C\u002Fp>\n\u003Ch2 id=\"section-36\">哪些已确认、哪些是制造商声明、哪些仍未知\u003C\u002Fh2>\n\u003Cp>\u003Cstrong>NVIDIA 已确认：\u003C\u002Fstrong>RTX Spark 是一个基于 Blackwell RTX 显卡和 Grace CPU 构建的 Windows PC 平台；系统可提供高达 128 GB 的统一内存；支持 DLSS 5 和 RTX 游戏技术栈；Nemotron 3.5 Bolt E4B 4GB 已向开发者开放；该模型支持 64K 上下文、工具使用、可配置推理和游戏状态接地。\u003C\u002Fp>\n\u003Cp>\u003Cstrong>制造商基准测试声明：\u003C\u002Fstrong>NVIDIA 报告称，在选定基准测试中，其平均质量比上一代模型高出约 40%，与同类产品相比输出 token 最多减少约 80%，并且 10 月版 DLSS 5 模型的运行速度是 9 月版本的两倍，同时将 GPU 开销减半，并将 4K 显存占用降低 20%。\u003C\u002Fp>\n\u003Cp>\u003Cstrong>本次公告中仍未知的信息：\u003C\u002Fstrong>在不同 RTX Spark 系统上同时进行渲染、语音和角色推理对实际帧时间的影响；游戏负载下 NPC 响应延迟的独立测量结果；将有多少商业游戏采用 Nemotron 3.5 Bolt；以及开发者将如何平衡本地 AI 质量与确定性游戏玩法和硬件要求。\u003C\u002Fp>\n\u003Ch2 id=\"section-40\">Figure Rocks 的观点\u003C\u002Fh2>\n\u003Cp>NVIDIA 10 月 27 日公告中最重要的部分不是某一项基准测试或某一个 AI NPC 演示。而是游戏 PC 作为共享 AI 运行时的新兴理念。神经图形、语音、检索、推理和游戏逻辑越来越多地在相同的帧时间和内存范围内竞争与合作。\u003C\u002Fp>\n\u003Cp>如果该架构在真实负载下能够正常工作，本地 AI 角色可能会减少对云端往返的依赖，并与实时游戏状态更紧密地连接，同时神经渲染继续为图像本身消耗 AI 算力。这是游戏构建方式的一次有意义的变化：问题从游戏是否使用 AI 转变为哪些 AI 工作负载值得获得本地资源、它们应在何时运行，以及每个工作负载获得何种权限。\u003C\u002Fp>\n\u003Ch2 id=\"section-43\">主要来源与范围\u003C\u002Fh2>\n\u003Cp>本文主要基于 NVIDIA 的 \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fnvidia-rtx-spark-powers-neural-rendering-and-ai-characters-in-games\u002F'>2026 年 10 月 27 日 RTX Spark 游戏公告\u003C\u002Fa>、10 月 23 日发布的 \u003Ca href='https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fnemotron\u002FNVIDIA-Nemotron-3.5-Bolt-E4B-4GB\u002F'>Nemotron 3.5 Bolt E4B 4GB 研究发布\u003C\u002Fa>，以及 NVIDIA 的 \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fbuild-on-device-ai-companions-with-the-nvidia-ace-game-agent-sdk-and-unreal-engine-5-plugins\u002F'>ACE Game Agent SDK 文档和示例\u003C\u002Fa>。\u003C\u002Fp>\n\u003Cp>在 NVIDIA 提供性能或质量数据的地方，除非有独立证据可用，Figure Rocks 将其视为供应商报告的测量结果。产品支持、游戏采用和运行时行为可能会随着 SDK、驱动程序和游戏集成的演进而变化。\u003C\u002Fp>",{"time":538,"blocks":539,"version":722},1793177027395,[540,545,549,554,558,562,566,570,574,578,582,586,590,594,598,602,606,610,614,618,622,626,630,634,638,642,646,650,654,658,662,666,670,674,678,682,686,690,694,698,702,706,710,714,718],{"id":541,"data":542,"type":544},"rtxspark-intro-1",{"text":543},"2026年10月27日，NVIDIA将RTX Spark定位为不止是一个新的Windows PC平台。该公司将两种不同的AI工作负载带到同一台游戏机上：通过DLSS 5实现的神经渲染，以及通过NVIDIA ACE和Nemotron 3.5 Bolt E4B 4GB实现的本地角色智能。","paragraph",{"id":546,"data":547,"type":544},"rtxspark-intro-2",{"text":548},"这种组合才是真正的新闻。游戏开始使用本地AI不仅是为了重建或生成像素，还为了解读玩家意图、对游戏状态进行推理、调用工具并驱动角色行为。技术挑战不再仅仅是模型能否运行，而是图形、语音和代理推理能否共享内存、计算和延迟预算，同时不损害游戏本身。",{"id":550,"data":551,"type":553},"rtxspark-h2-direct",{"text":552,"level":47},"直接回答","header",{"id":555,"data":556,"type":544},"rtxspark-direct-1",{"text":557},"RTX Spark是NVIDIA的新Windows PC平台，用于AI开发、创作和游戏，围绕Blackwell RTX GPU和Grace CPU构建，最高支持128 GB统一内存。对于游戏，NVIDIA将该平台与DLSS 5、RTX Kit、虚幻引擎5.8支持以及新的小型语言模型Nemotron 3.5 Bolt E4B 4GB配对，专为本地AI角色设计。",{"id":559,"data":560,"type":544},"rtxspark-direct-2",{"text":561},"最重要的架构变化是神经图形和游戏代理推理正在成为并发工作负载。未来的游戏可能使用一条AI路径来改善渲染图像，而另一个模型则倾听玩家、读取相关状态、对请求进行推理并选择允许的游戏动作。",{"id":563,"data":564,"type":553},"rtxspark-h2-announcement",{"text":565,"level":47},"NVIDIA在2026年10月27日宣布了什么",{"id":567,"data":568,"type":544},"rtxspark-announcement-1",{"text":569},"NVIDIA表示，RTX Spark将高达128 GB的统一内存与CUDA软件栈、光线追踪和完整的DLSS套件相结合。游戏栈还包括RTX Kit技术、Nsight开发工具、虚幻引擎5.8的RTX分支以及用于运行本地语言和语音模型的游戏内推理SDK。",{"id":571,"data":572,"type":544},"rtxspark-announcement-2",{"text":573},"角色方面的更新以Nemotron 3.5 Bolt E4B 4GB为中心。NVIDIA于10月23日发布了该模型本身，四天后又强调了其在游戏中的作用。该模型可通过游戏内推理SDK提供给开发者，并针对需要在本地运行同时为应用程序其余部分保留资源的对话代理进行了优化。",{"id":575,"data":576,"type":544},"rtxspark-announcement-3",{"text":577},"在渲染方面，RTX Spark支持带有3D引导神经渲染的DLSS 5，首发于NBA 2K27。NVIDIA表示，其10月DLSS 5模型更新运行速度是9月版本的两倍，GPU开销减半，在4K下使用的VRAM减少20%，同时保持相当的视觉保真度。这些是NVIDIA的测量结果，在独立测试之前应视为制造商的性能声明。",{"id":579,"data":580,"type":553},"rtxspark-h2-shared",{"text":581,"level":47},"真正的转变：游戏PC成为共享AI运行时",{"id":583,"data":584,"type":544},"rtxspark-shared-1",{"text":585},"本地游戏AI比桌面聊天机器人面临更严格的约束：它并不拥有这台机器。游戏已经在消耗GPU时间、内存带宽、VRAM或统一内存、CPU时间、存储带宽和帧时间预算。语音识别和文本转语音可能增加另一层竞争。",{"id":587,"data":588,"type":544},"rtxspark-shared-2",{"text":589},"这使得每GB的效率比原始模型大小更重要。NVIDIA描述Nemotron 3.5 Bolt E4B在其目标工作负载中仅占用约4 GB，以便本地角色推理可以与图形和其他模型共存。因此，设计目标不仅仅是更聪明的NPC，而是一个在游戏仍在渲染时仍能保持有用的模型。",{"id":591,"data":592,"type":544},"rtxspark-shared-3",{"text":593},"这也是为什么RTX Spark作为一个平台故事而非单一模型公告很重要。神经渲染、语言推理、语音和传统游戏逻辑正在同一台机器上融合，但它们仍然有不同的时序要求和对游戏的不同权限。",{"id":595,"data":596,"type":553},"rtxspark-h2-bolt",{"text":597,"level":47},"Nemotron 3.5 Bolt为本地游戏角色增加了什么",{"id":599,"data":600,"type":544},"rtxspark-bolt-1",{"text":601},"Nemotron 3.5 Bolt E4B 4GB专为对话和代理工作负载而构建，而非逐帧控制。NVIDIA将其核心能力列为自主多轮工具使用、指令遵循、可配置推理和基于游戏状态的接地。",{"id":603,"data":604,"type":544},"rtxspark-bolt-2",{"text":605},"该模型支持64K上下文窗口，可容纳对话历史、指令、工具定义、检索信息和游戏状态。它还支持35种语言，而NVIDIA表示基础模型在超过140种语言上进行了预训练。",{"id":607,"data":608,"type":544},"rtxspark-bolt-3",{"text":609},"NVIDIA报告称，在选定的相关基准测试中，其平均质量比上一代模型高出约40%，输出令牌比同类模型少约80%。这些数字描述的是NVIDIA的基准测试结果，并不保证NPC可信度、游戏延迟或帧节奏的改善。",{"id":611,"data":612,"type":544},"rtxspark-bolt-4",{"text":613},"还有一个重要的时间线区别。PUBG的公测AI队友使用NVIDIA的第一代Nemotron小型语言模型，而Aniimo展示了第二代Nemotron模型。Nemotron 3.5 Bolt是现在宣布的新开发者模型；NVIDIA并未表示那些现有实现已经迁移到它。",{"id":615,"data":616,"type":544},"rtxspark-bolt-5",{"text":617},"Figure Rocks 已在 \u003Ca href='\u002Fzh\u002Fblog\u002Fpubg-ally-shows-why-ai-teammates-need-two-brains-fast-reflexes-and-slow-reasoning'>PUBG Ally 展示了为什么 AI 队友需要两个大脑\u003C\u002Fa> 中探讨了这种分离：语言推理对于规划、协调和解释很有用，而快速战斗反应仍然属于确定性或专门的游戏侧系统。",{"id":619,"data":620,"type":553},"rtxspark-h2-context",{"text":621,"level":47},"64K 上下文、检索、实时状态和工具不是一回事",{"id":623,"data":624,"type":544},"rtxspark-context-1",{"text":625},"64K 上下文窗口增加了模型一次可以考虑的信息量，但它并不会自动让角色变得知识渊博、与时俱进或正确。上下文容量回答的是可以供给多少信息。检索决定应该供给哪些外部知识。实时游戏状态描述当前会话中什么是真实的。工具定义智能体被允许检查或做什么。",{"id":627,"data":628,"type":544},"rtxspark-context-2",{"text":629},"NVIDIA 的 ACE Game Agent SDK 直接反映了这种分离。其 Agent API 管理有状态、多步骤的工具辅助推理；其 Chat API 为开发者提供对推理的更低层级控制；其 RAG API 支持从开发者构建的数据库中进行语义、词汇和混合检索。NVIDIA 已在实验性的《全面战争：法老》顾问中展示了该检索架构，该顾问查询了超过 1,200 个相互关联的游戏数据表。",{"id":631,"data":632,"type":544},"rtxspark-context-3",{"text":633},"对于游戏角色，这些层应保持独立。知识数据库可能说明某个物品如何运作。当前游戏状态必须说明该物品是否实际存在。模型可能判断使用该物品是合理的。一个经过验证的游戏侧函数仍必须决定该动作是否合法并执行它。",{"id":635,"data":636,"type":544},"rtxspark-context-4",{"text":637},"本地推理也不意味着整个游戏变得离线。语言模型可能在玩家机器上运行，而多人服务器、账户系统、可下载内容或其他服务仍需要网络连接。",{"id":639,"data":640,"type":553},"rtxspark-h2-dlss",{"text":641,"level":47},"DLSS 5 让同一台机器成为 AI 渲染平台",{"id":643,"data":644,"type":544},"rtxspark-dlss-1",{"text":645},"DLSS 5 引入了 3D 引导神经渲染，作为图形管线中的另一个阶段。NVIDIA 将其描述为从引擎渲染的帧中增强光照和材质细节，同时保留开发者对可更改内容的控制。现有几何体、纹理、光照缓冲区和创作场景仍是基础。",{"id":647,"data":648,"type":544},"rtxspark-dlss-2",{"text":649},"这种区分很重要，因为神经渲染不是游戏引擎的替代品。它是在引擎已提供的信息上运行的推理层。同样的原则也出现在智能体一侧：语言模型可以解释和决策，但游戏引擎仍对有效状态和可执行动作拥有权威。",{"id":651,"data":652,"type":544},"rtxspark-dlss-3",{"text":653},"更广泛的架构在 \u003Ca href='\u002Fzh\u002Fblog\u002Fthe-game-engine-is-becoming-part-renderer-part-scheduler-part-ai-system'>游戏引擎正变得部分渲染器、部分调度器、部分 AI 系统\u003C\u002Fa> 中进行了探讨。RTX Spark 使这种融合更加具体，因为渲染推理和智能体推理现在被设计为必须在一个本地系统上共存的工作负载。",{"id":655,"data":656,"type":553},"rtxspark-h2-dev",{"text":657,"level":47},"为什么 RTX Spark 对游戏开发者很重要",{"id":659,"data":660,"type":544},"rtxspark-dev-1",{"text":661},"RTX Spark 不仅仅是消费级功能捆绑。NVIDIA 围绕它提供了一条开发路径：虚幻引擎 5.8 对 Windows on Arm 的支持、Nsight 性能分析工具、游戏内推理 SDK 以及八项 RTX Kit 技术，涵盖神经纹理压缩、神经着色器、几何体、降噪、角色渲染和全局光照等领域。",{"id":663,"data":664,"type":544},"rtxspark-dev-2",{"text":665},"实际意义在于，开发者可以越来越多地将图形和本地 AI 作为同一运行时预算的一部分进行分析，而不是将 AI 视为具有单独延迟和成本假设的远程服务。这创造了新的可能性，但也使调度、内存压力和最坏情况下的帧时间行为变得更加重要。",{"id":667,"data":668,"type":553},"rtxspark-h2-players",{"text":669,"level":47},"玩家目前不应假设什么",{"id":671,"data":672,"type":544},"rtxspark-players-1",{"text":673},"支持 RTX Spark 并不意味着每款游戏都会突然包含非脚本化的 AI 角色。开发者仍需设计角色、暴露安全的观察和动作、集成语音或文本交互、定义记忆行为，并决定模型推理何时值得运行时成本。",{"id":675,"data":676,"type":544},"rtxspark-players-2",{"text":677},"DLSS 5 的性能声明也不能证明每款受支持的游戏都会感觉更响应。更高的显示帧率、生成的帧、神经重建质量和输入延迟是相关但独立的测量指标。图形功能可以改善视觉流畅度，而不会降低端到端延迟的每个组成部分。",{"id":679,"data":680,"type":544},"rtxspark-players-3",{"text":681},"同样，更强大的本地语言模型并不会使游戏行为变得确定性。开放式对话和推理可以提高适应性，但对于正确响应已知的行为，脚本化系统仍然更容易测试且更可预测。",{"id":683,"data":684,"type":553},"rtxspark-h2-evidence",{"text":685,"level":47},"哪些已确认、哪些是制造商声明、哪些仍未知",{"id":687,"data":688,"type":544},"rtxspark-evidence-1",{"text":689},"\u003Cstrong>NVIDIA 已确认：\u003C\u002Fstrong>RTX Spark 是一个基于 Blackwell RTX 显卡和 Grace CPU 构建的 Windows PC 平台；系统可提供高达 128 GB 的统一内存；支持 DLSS 5 和 RTX 游戏技术栈；Nemotron 3.5 Bolt E4B 4GB 已向开发者开放；该模型支持 64K 上下文、工具使用、可配置推理和游戏状态接地。",{"id":691,"data":692,"type":544},"rtxspark-evidence-2",{"text":693},"\u003Cstrong>制造商基准测试声明：\u003C\u002Fstrong>NVIDIA 报告称，在选定基准测试中，其平均质量比上一代模型高出约 40%，与同类产品相比输出 token 最多减少约 80%，并且 10 月版 DLSS 5 模型的运行速度是 9 月版本的两倍，同时将 GPU 开销减半，并将 4K 显存占用降低 20%。",{"id":695,"data":696,"type":544},"rtxspark-evidence-3",{"text":697},"\u003Cstrong>本次公告中仍未知的信息：\u003C\u002Fstrong>在不同 RTX Spark 系统上同时进行渲染、语音和角色推理对实际帧时间的影响；游戏负载下 NPC 响应延迟的独立测量结果；将有多少商业游戏采用 Nemotron 3.5 Bolt；以及开发者将如何平衡本地 AI 质量与确定性游戏玩法和硬件要求。",{"id":699,"data":700,"type":553},"rtxspark-h2-take",{"text":701,"level":47},"Figure Rocks 的观点",{"id":703,"data":704,"type":544},"rtxspark-take-1",{"text":705},"NVIDIA 10 月 27 日公告中最重要的部分不是某一项基准测试或某一个 AI NPC 演示。而是游戏 PC 作为共享 AI 运行时的新兴理念。神经图形、语音、检索、推理和游戏逻辑越来越多地在相同的帧时间和内存范围内竞争与合作。",{"id":707,"data":708,"type":544},"rtxspark-take-2",{"text":709},"如果该架构在真实负载下能够正常工作，本地 AI 角色可能会减少对云端往返的依赖，并与实时游戏状态更紧密地连接，同时神经渲染继续为图像本身消耗 AI 算力。这是游戏构建方式的一次有意义的变化：问题从游戏是否使用 AI 转变为哪些 AI 工作负载值得获得本地资源、它们应在何时运行，以及每个工作负载获得何种权限。",{"id":711,"data":712,"type":553},"rtxspark-h2-sources",{"text":713,"level":47},"主要来源与范围",{"id":715,"data":716,"type":544},"rtxspark-sources-1",{"text":717},"本文主要基于 NVIDIA 的 \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fnvidia-rtx-spark-powers-neural-rendering-and-ai-characters-in-games\u002F'>2026 年 10 月 27 日 RTX Spark 游戏公告\u003C\u002Fa>、10 月 23 日发布的 \u003Ca href='https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fnemotron\u002FNVIDIA-Nemotron-3.5-Bolt-E4B-4GB\u002F'>Nemotron 3.5 Bolt E4B 4GB 研究发布\u003C\u002Fa>，以及 NVIDIA 的 \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fbuild-on-device-ai-companions-with-the-nvidia-ace-game-agent-sdk-and-unreal-engine-5-plugins\u002F'>ACE Game Agent SDK 文档和示例\u003C\u002Fa>。",{"id":719,"data":720,"type":544},"rtxspark-sources-2",{"text":721},"在 NVIDIA 提供性能或质量数据的地方，除非有独立证据可用，Figure Rocks 将其视为供应商报告的测量结果。产品支持、游戏采用和运行时行为可能会随着 SDK、驱动程序和游戏集成的演进而变化。","2.31","NVIDIA 正将神经渲染与本地 AI 角色推理引入同一个游戏平台。RTX Spark、DLSS 5 和 Nemotron 3.5 Bolt 表明，下一个挑战不仅仅是让 AI 在游戏中运行，而是让图形、语音和智能体推理共存，同时不破坏体验。","\u002Fuploads\u002F2026\u002F10\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform-1793176725927-jsji28.webp","nvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform-1793176725927-jsji28",false,"PUBLISHED","2026-10-28T06:37:00.000Z","2026-10-28T08:37:23.031Z","2026-10-28T08:48:15.292Z",{"en":732,"de":733,"sr":734,"es":735,"fr":736,"it":737,"ru":738,"zh":739},"\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u002Fde\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u002Fsr\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u002Fes\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u002Ffr\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u002Fit\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u002Fru\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform","\u002Fzh\u002Fblog\u002Fnvidia-rtx-spark-puts-dlss-5-and-local-ai-characters-on-the-same-gaming-platform",[741,745,749],{"id":742,"name":743,"slug":744},166,"游戏新闻","gaming-news",{"id":746,"name":747,"slug":748},82,"装备","gear",{"id":750,"name":751,"slug":752},43,"体验","experience",{"id":283,"login":754,"email":13,"displayName":755},"aleksandar","Aleksandar Stajic",[757,900],{"lang":8,"title":758,"content":759,"contentJson":760,"excerpt":899},"NVIDIA RTX Spark Puts DLSS 5 and Local AI Characters on the Same Gaming Platform","{\"time\":1793176200000,\"blocks\":[{\"id\":\"rtxspark-intro-1\",\"data\":{\"text\":\"On October 27, 2026, NVIDIA positioned RTX Spark as more than a new Windows PC platform. The company is bringing two different kinds of AI workload onto the same gaming machine: neural rendering through DLSS 5 and local character intelligence through NVIDIA ACE and Nemotron 3.5 Bolt E4B 4GB.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-intro-2\",\"data\":{\"text\":\"That combination is the real news. Games are beginning to use local AI not only to reconstruct or generate pixels, but also to interpret player intent, reason over game state, call tools and drive character behavior. The technical challenge is no longer only whether a model can run. It is whether graphics, speech and agent inference can share memory, compute and latency budgets without damaging the game itself.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-direct\",\"data\":{\"text\":\"Direct answer\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-direct-1\",\"data\":{\"text\":\"RTX Spark is NVIDIA's new Windows PC platform for AI development, creation and gaming, built around a Blackwell RTX GPU and Grace CPU with up to 128 GB of unified memory. For games, NVIDIA is pairing that platform with DLSS 5, RTX Kit, Unreal Engine 5.8 support and a new small language model, Nemotron 3.5 Bolt E4B 4GB, designed for local AI characters.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-direct-2\",\"data\":{\"text\":\"The most important architectural change is that neural graphics and game-agent reasoning are becoming concurrent workloads. A future game may use one AI path to improve the rendered image while another model listens to the player, reads relevant state, reasons about a request and selects an allowed game action.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-announcement\",\"data\":{\"text\":\"What NVIDIA announced on October 27, 2026\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-announcement-1\",\"data\":{\"text\":\"NVIDIA says RTX Spark combines up to 128 GB of unified memory with the CUDA software stack, ray tracing and the full DLSS suite. The gaming stack also includes RTX Kit technologies, Nsight development tools, an RTX Branch of Unreal Engine 5.8 and the In-Game Inferencing SDK used to run local language and speech models.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-announcement-2\",\"data\":{\"text\":\"The character-side update centers on Nemotron 3.5 Bolt E4B 4GB. NVIDIA released the model itself on October 23, then highlighted its gaming role four days later. The model is available to developers through the In-Game Inferencing SDK and is optimized for conversational agents that need to run locally while leaving resources available for the rest of the application.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-announcement-3\",\"data\":{\"text\":\"On the rendering side, DLSS 5 with 3D-Guided Neural Rendering is supported on RTX Spark, beginning with NBA 2K27. NVIDIA says its October DLSS 5 model update runs twice as fast as the September version, halves GPU overhead and uses 20% less VRAM at 4K while maintaining comparable visual fidelity. Those are NVIDIA's measurements and should be treated as manufacturer performance claims until independently tested.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-shared\",\"data\":{\"text\":\"The real shift: the gaming PC becomes a shared AI runtime\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-shared-1\",\"data\":{\"text\":\"Local game AI has a harder constraint than a desktop chatbot: it does not own the machine. The game is already consuming GPU time, memory bandwidth, VRAM or unified memory, CPU time, storage bandwidth and frame-time budget. Speech recognition and text-to-speech can add another layer of competition.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-shared-2\",\"data\":{\"text\":\"That makes efficiency per gigabyte more important than raw model size. NVIDIA describes Nemotron 3.5 Bolt E4B as fitting into roughly 4 GB for its target workloads so that local character inference can coexist with graphics and other models. The design goal is therefore not simply a smarter NPC. It is a model that can remain useful while the game is still rendering.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-shared-3\",\"data\":{\"text\":\"This is also why RTX Spark matters as a platform story rather than as a single-model announcement. Neural rendering, language reasoning, speech and traditional game logic are converging on the same machine, but they still have different timing requirements and different authority over the game.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-bolt\",\"data\":{\"text\":\"What Nemotron 3.5 Bolt adds to local game characters\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-bolt-1\",\"data\":{\"text\":\"Nemotron 3.5 Bolt E4B 4GB is built for conversational and agentic workloads rather than frame-by-frame control. NVIDIA lists autonomous multi-turn tool use, instruction adherence, configurable reasoning and grounding to game state among its core capabilities.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-bolt-2\",\"data\":{\"text\":\"The model supports a 64K context window that can hold conversation history, instructions, tool definitions, retrieved information and game state. It also supports 35 languages, while NVIDIA says the base model was pretrained across more than 140 languages.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-bolt-3\",\"data\":{\"text\":\"NVIDIA reports about 40% higher average quality than its previous model on selected relevant benchmarks and up to about 80% fewer output tokens than peer models. These numbers describe NVIDIA's benchmark results, not a guaranteed improvement in NPC believability, game latency or frame pacing.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-bolt-4\",\"data\":{\"text\":\"There is also an important timeline distinction. PUBG's public-beta AI teammate uses NVIDIA's first-generation Nemotron small language model, while Aniimo demonstrated a second-generation Nemotron model. Nemotron 3.5 Bolt is the new developer model announced now; NVIDIA has not said that those existing implementations have already migrated to it.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-bolt-5\",\"data\":{\"text\":\"Figure Rocks already examined that separation in \u003Ca href='\u002Fblog\u002Fpubg-ally-shows-why-ai-teammates-need-two-brains-fast-reflexes-and-slow-reasoning'>PUBG Ally Shows Why AI Teammates Need Two Brains\u003C\u002Fa>: language reasoning is useful for planning, coordination and interpretation, while fast combat reactions still belong in deterministic or specialized game-side systems.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-context\",\"data\":{\"text\":\"64K context, retrieval, live state and tools are not the same thing\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-context-1\",\"data\":{\"text\":\"A 64K context window increases how much information a model can consider at once, but it does not automatically make the character knowledgeable, current or correct. Context capacity answers how much information can be supplied. Retrieval decides which external knowledge should be supplied. Live game state describes what is true in the current session. Tools define what the agent is allowed to inspect or do.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-context-2\",\"data\":{\"text\":\"NVIDIA's ACE Game Agent SDK reflects that separation directly. Its Agent API manages stateful, multi-step tool-assisted reasoning; its Chat API gives developers lower-level control over inference; and its RAG API supports semantic, lexical and hybrid retrieval from developer-built databases. NVIDIA has already demonstrated that retrieval architecture in the experimental Total War: PHARAOH advisor, which queries more than 1,200 interlinked game-data tables.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-context-3\",\"data\":{\"text\":\"For a game character, those layers should stay distinct. A knowledge database may say how an item works. Current game state must say whether the item is actually present. The model may decide that using the item is sensible. A validated game-side function must still decide whether that action is legal and execute it.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-context-4\",\"data\":{\"text\":\"Local inference also does not mean that the entire game becomes offline. The language model may run on the player's machine while multiplayer servers, account systems, downloadable content or other services still require a network connection.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-dlss\",\"data\":{\"text\":\"DLSS 5 makes the same machine an AI rendering platform\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-dlss-1\",\"data\":{\"text\":\"DLSS 5 introduces 3D-Guided Neural Rendering as another stage in the graphics pipeline. NVIDIA describes it as enhancing lighting and material detail from the engine-rendered frame while preserving developer controls over what can change. The existing geometry, textures, lighting buffers and authored scene remain the foundation.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-dlss-2\",\"data\":{\"text\":\"That distinction matters because neural rendering is not a replacement for the game engine. It is an inference layer operating on information the engine already provides. The same principle appears on the agent side: a language model can interpret and decide, but the game engine remains authoritative over valid state and executable actions.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-dlss-3\",\"data\":{\"text\":\"The broader architecture is explored in \u003Ca href='\u002Fblog\u002Fthe-game-engine-is-becoming-part-renderer-part-scheduler-part-ai-system'>The Game Engine Is Becoming Part Renderer, Part Scheduler, Part AI System\u003C\u002Fa>. RTX Spark makes that convergence more concrete because rendering inference and agent inference are now being designed as workloads that must coexist on one local system.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-dev\",\"data\":{\"text\":\"Why RTX Spark matters to game developers\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-dev-1\",\"data\":{\"text\":\"RTX Spark is not only a consumer feature bundle. NVIDIA is providing a development path around it: Unreal Engine 5.8 support for Windows on Arm, Nsight profiling tools, the In-Game Inferencing SDK and eight RTX Kit technologies covering areas such as neural texture compression, neural shaders, geometry, denoising, character rendering and global illumination.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-dev-2\",\"data\":{\"text\":\"The practical implication is that developers can increasingly profile graphics and local AI as parts of one runtime budget instead of treating AI as a remote service with separate latency and cost assumptions. That creates new possibilities, but it also makes scheduling, memory pressure and worst-case frame-time behavior more important.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-players\",\"data\":{\"text\":\"What players should not assume yet\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-players-1\",\"data\":{\"text\":\"RTX Spark support does not mean that every game will suddenly contain unscripted AI characters. Developers still have to design the character, expose safe observations and actions, integrate speech or text interaction, define memory behavior and decide when model inference is worth the runtime cost.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-players-2\",\"data\":{\"text\":\"DLSS 5 performance claims also do not prove that every supported game will feel more responsive. Higher displayed frame rates, generated frames, neural reconstruction quality and input latency are related but separate measurements. A graphics feature can improve visual smoothness without reducing every component of end-to-end latency.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-players-3\",\"data\":{\"text\":\"Likewise, a stronger local language model does not make game behavior deterministic. Open-ended dialogue and reasoning can improve adaptability, but scripted systems remain easier to test and more predictable for behaviors where the correct response is already known.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-evidence\",\"data\":{\"text\":\"What is confirmed, what is a manufacturer claim, and what is still unknown\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-evidence-1\",\"data\":{\"text\":\"\u003Cstrong>Confirmed by NVIDIA:\u003C\u002Fstrong> RTX Spark is a Windows PC platform built around Blackwell RTX graphics and Grace CPUs; systems can provide up to 128 GB of unified memory; DLSS 5 and the RTX gaming stack are supported; Nemotron 3.5 Bolt E4B 4GB is available to developers; the model supports 64K context, tool use, configurable reasoning and game-state grounding.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-evidence-2\",\"data\":{\"text\":\"\u003Cstrong>Manufacturer benchmark claims:\u003C\u002Fstrong> NVIDIA reports roughly 40% higher average quality than its previous model on selected benchmarks, up to roughly 80% fewer output tokens versus peers, and an October DLSS 5 model that runs twice as fast as the September version while halving GPU overhead and reducing 4K VRAM use by 20%.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-evidence-3\",\"data\":{\"text\":\"\u003Cstrong>Still unknown from this announcement:\u003C\u002Fstrong> the real frame-time impact of simultaneous rendering, speech and character inference across different RTX Spark systems; independent measurements of NPC response latency under game load; how many commercial games will adopt Nemotron 3.5 Bolt; and how developers will balance local AI quality against deterministic gameplay and hardware requirements.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-take\",\"data\":{\"text\":\"The Figure Rocks take\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-take-1\",\"data\":{\"text\":\"The most important part of NVIDIA's October 27 announcement is not one benchmark or one AI NPC demo. It is the emerging idea of the gaming PC as a shared AI runtime. Neural graphics, speech, retrieval, reasoning and game logic increasingly compete and cooperate inside the same frame-time and memory envelope.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-take-2\",\"data\":{\"text\":\"If that architecture works under real load, local AI characters could become less dependent on cloud round trips and more tightly connected to live game state, while neural rendering continues to consume AI compute for the image itself. That is a meaningful change in how games are built: the question shifts from whether a game uses AI to which AI workloads deserve local resources, when they should run, and what authority each one receives.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-h2-sources\",\"data\":{\"text\":\"Primary sources and scope\",\"level\":2},\"type\":\"header\"},{\"id\":\"rtxspark-sources-1\",\"data\":{\"text\":\"This article is based primarily on NVIDIA's \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fnvidia-rtx-spark-powers-neural-rendering-and-ai-characters-in-games\u002F'>October 27, 2026 RTX Spark gaming announcement\u003C\u002Fa>, the \u003Ca href='https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fnemotron\u002FNVIDIA-Nemotron-3.5-Bolt-E4B-4GB\u002F'>Nemotron 3.5 Bolt E4B 4GB research release\u003C\u002Fa> published October 23, and NVIDIA's \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fbuild-on-device-ai-companions-with-the-nvidia-ace-game-agent-sdk-and-unreal-engine-5-plugins\u002F'>ACE Game Agent SDK documentation and examples\u003C\u002Fa>.\"},\"type\":\"paragraph\"},{\"id\":\"rtxspark-sources-2\",\"data\":{\"text\":\"Where NVIDIA provides performance or quality numbers, Figure Rocks treats them as vendor-reported measurements unless independent evidence is available. Product support, game adoption and runtime behavior can change as SDKs, drivers and game integrations evolve.\"},\"type\":\"paragraph\"}],\"version\":\"2.31.0\"}",{"time":761,"blocks":762,"version":898},1793176200000,[763,766,769,772,775,778,781,784,787,790,793,796,799,802,805,808,811,814,817,820,823,826,829,832,835,838,841,844,847,850,853,856,859,862,865,868,871,874,877,880,883,886,889,892,895],{"id":541,"data":764,"type":544},{"text":765},"On October 27, 2026, NVIDIA positioned RTX Spark as more than a new Windows PC platform. The company is bringing two different kinds of AI workload onto the same gaming machine: neural rendering through DLSS 5 and local character intelligence through NVIDIA ACE and Nemotron 3.5 Bolt E4B 4GB.",{"id":546,"data":767,"type":544},{"text":768},"That combination is the real news. Games are beginning to use local AI not only to reconstruct or generate pixels, but also to interpret player intent, reason over game state, call tools and drive character behavior. The technical challenge is no longer only whether a model can run. It is whether graphics, speech and agent inference can share memory, compute and latency budgets without damaging the game itself.",{"id":550,"data":770,"type":553},{"text":771,"level":47},"Direct answer",{"id":555,"data":773,"type":544},{"text":774},"RTX Spark is NVIDIA's new Windows PC platform for AI development, creation and gaming, built around a Blackwell RTX GPU and Grace CPU with up to 128 GB of unified memory. For games, NVIDIA is pairing that platform with DLSS 5, RTX Kit, Unreal Engine 5.8 support and a new small language model, Nemotron 3.5 Bolt E4B 4GB, designed for local AI characters.",{"id":559,"data":776,"type":544},{"text":777},"The most important architectural change is that neural graphics and game-agent reasoning are becoming concurrent workloads. A future game may use one AI path to improve the rendered image while another model listens to the player, reads relevant state, reasons about a request and selects an allowed game action.",{"id":563,"data":779,"type":553},{"text":780,"level":47},"What NVIDIA announced on October 27, 2026",{"id":567,"data":782,"type":544},{"text":783},"NVIDIA says RTX Spark combines up to 128 GB of unified memory with the CUDA software stack, ray tracing and the full DLSS suite. The gaming stack also includes RTX Kit technologies, Nsight development tools, an RTX Branch of Unreal Engine 5.8 and the In-Game Inferencing SDK used to run local language and speech models.",{"id":571,"data":785,"type":544},{"text":786},"The character-side update centers on Nemotron 3.5 Bolt E4B 4GB. NVIDIA released the model itself on October 23, then highlighted its gaming role four days later. The model is available to developers through the In-Game Inferencing SDK and is optimized for conversational agents that need to run locally while leaving resources available for the rest of the application.",{"id":575,"data":788,"type":544},{"text":789},"On the rendering side, DLSS 5 with 3D-Guided Neural Rendering is supported on RTX Spark, beginning with NBA 2K27. NVIDIA says its October DLSS 5 model update runs twice as fast as the September version, halves GPU overhead and uses 20% less VRAM at 4K while maintaining comparable visual fidelity. Those are NVIDIA's measurements and should be treated as manufacturer performance claims until independently tested.",{"id":579,"data":791,"type":553},{"text":792,"level":47},"The real shift: the gaming PC becomes a shared AI runtime",{"id":583,"data":794,"type":544},{"text":795},"Local game AI has a harder constraint than a desktop chatbot: it does not own the machine. The game is already consuming GPU time, memory bandwidth, VRAM or unified memory, CPU time, storage bandwidth and frame-time budget. Speech recognition and text-to-speech can add another layer of competition.",{"id":587,"data":797,"type":544},{"text":798},"That makes efficiency per gigabyte more important than raw model size. NVIDIA describes Nemotron 3.5 Bolt E4B as fitting into roughly 4 GB for its target workloads so that local character inference can coexist with graphics and other models. The design goal is therefore not simply a smarter NPC. It is a model that can remain useful while the game is still rendering.",{"id":591,"data":800,"type":544},{"text":801},"This is also why RTX Spark matters as a platform story rather than as a single-model announcement. Neural rendering, language reasoning, speech and traditional game logic are converging on the same machine, but they still have different timing requirements and different authority over the game.",{"id":595,"data":803,"type":553},{"text":804,"level":47},"What Nemotron 3.5 Bolt adds to local game characters",{"id":599,"data":806,"type":544},{"text":807},"Nemotron 3.5 Bolt E4B 4GB is built for conversational and agentic workloads rather than frame-by-frame control. NVIDIA lists autonomous multi-turn tool use, instruction adherence, configurable reasoning and grounding to game state among its core capabilities.",{"id":603,"data":809,"type":544},{"text":810},"The model supports a 64K context window that can hold conversation history, instructions, tool definitions, retrieved information and game state. It also supports 35 languages, while NVIDIA says the base model was pretrained across more than 140 languages.",{"id":607,"data":812,"type":544},{"text":813},"NVIDIA reports about 40% higher average quality than its previous model on selected relevant benchmarks and up to about 80% fewer output tokens than peer models. These numbers describe NVIDIA's benchmark results, not a guaranteed improvement in NPC believability, game latency or frame pacing.",{"id":611,"data":815,"type":544},{"text":816},"There is also an important timeline distinction. PUBG's public-beta AI teammate uses NVIDIA's first-generation Nemotron small language model, while Aniimo demonstrated a second-generation Nemotron model. Nemotron 3.5 Bolt is the new developer model announced now; NVIDIA has not said that those existing implementations have already migrated to it.",{"id":615,"data":818,"type":544},{"text":819},"Figure Rocks already examined that separation in \u003Ca href='\u002Fblog\u002Fpubg-ally-shows-why-ai-teammates-need-two-brains-fast-reflexes-and-slow-reasoning'>PUBG Ally Shows Why AI Teammates Need Two Brains\u003C\u002Fa>: language reasoning is useful for planning, coordination and interpretation, while fast combat reactions still belong in deterministic or specialized game-side systems.",{"id":619,"data":821,"type":553},{"text":822,"level":47},"64K context, retrieval, live state and tools are not the same thing",{"id":623,"data":824,"type":544},{"text":825},"A 64K context window increases how much information a model can consider at once, but it does not automatically make the character knowledgeable, current or correct. Context capacity answers how much information can be supplied. Retrieval decides which external knowledge should be supplied. Live game state describes what is true in the current session. Tools define what the agent is allowed to inspect or do.",{"id":627,"data":827,"type":544},{"text":828},"NVIDIA's ACE Game Agent SDK reflects that separation directly. Its Agent API manages stateful, multi-step tool-assisted reasoning; its Chat API gives developers lower-level control over inference; and its RAG API supports semantic, lexical and hybrid retrieval from developer-built databases. NVIDIA has already demonstrated that retrieval architecture in the experimental Total War: PHARAOH advisor, which queries more than 1,200 interlinked game-data tables.",{"id":631,"data":830,"type":544},{"text":831},"For a game character, those layers should stay distinct. A knowledge database may say how an item works. Current game state must say whether the item is actually present. The model may decide that using the item is sensible. A validated game-side function must still decide whether that action is legal and execute it.",{"id":635,"data":833,"type":544},{"text":834},"Local inference also does not mean that the entire game becomes offline. The language model may run on the player's machine while multiplayer servers, account systems, downloadable content or other services still require a network connection.",{"id":639,"data":836,"type":553},{"text":837,"level":47},"DLSS 5 makes the same machine an AI rendering platform",{"id":643,"data":839,"type":544},{"text":840},"DLSS 5 introduces 3D-Guided Neural Rendering as another stage in the graphics pipeline. NVIDIA describes it as enhancing lighting and material detail from the engine-rendered frame while preserving developer controls over what can change. The existing geometry, textures, lighting buffers and authored scene remain the foundation.",{"id":647,"data":842,"type":544},{"text":843},"That distinction matters because neural rendering is not a replacement for the game engine. It is an inference layer operating on information the engine already provides. The same principle appears on the agent side: a language model can interpret and decide, but the game engine remains authoritative over valid state and executable actions.",{"id":651,"data":845,"type":544},{"text":846},"The broader architecture is explored in \u003Ca href='\u002Fblog\u002Fthe-game-engine-is-becoming-part-renderer-part-scheduler-part-ai-system'>The Game Engine Is Becoming Part Renderer, Part Scheduler, Part AI System\u003C\u002Fa>. RTX Spark makes that convergence more concrete because rendering inference and agent inference are now being designed as workloads that must coexist on one local system.",{"id":655,"data":848,"type":553},{"text":849,"level":47},"Why RTX Spark matters to game developers",{"id":659,"data":851,"type":544},{"text":852},"RTX Spark is not only a consumer feature bundle. NVIDIA is providing a development path around it: Unreal Engine 5.8 support for Windows on Arm, Nsight profiling tools, the In-Game Inferencing SDK and eight RTX Kit technologies covering areas such as neural texture compression, neural shaders, geometry, denoising, character rendering and global illumination.",{"id":663,"data":854,"type":544},{"text":855},"The practical implication is that developers can increasingly profile graphics and local AI as parts of one runtime budget instead of treating AI as a remote service with separate latency and cost assumptions. That creates new possibilities, but it also makes scheduling, memory pressure and worst-case frame-time behavior more important.",{"id":667,"data":857,"type":553},{"text":858,"level":47},"What players should not assume yet",{"id":671,"data":860,"type":544},{"text":861},"RTX Spark support does not mean that every game will suddenly contain unscripted AI characters. Developers still have to design the character, expose safe observations and actions, integrate speech or text interaction, define memory behavior and decide when model inference is worth the runtime cost.",{"id":675,"data":863,"type":544},{"text":864},"DLSS 5 performance claims also do not prove that every supported game will feel more responsive. Higher displayed frame rates, generated frames, neural reconstruction quality and input latency are related but separate measurements. A graphics feature can improve visual smoothness without reducing every component of end-to-end latency.",{"id":679,"data":866,"type":544},{"text":867},"Likewise, a stronger local language model does not make game behavior deterministic. Open-ended dialogue and reasoning can improve adaptability, but scripted systems remain easier to test and more predictable for behaviors where the correct response is already known.",{"id":683,"data":869,"type":553},{"text":870,"level":47},"What is confirmed, what is a manufacturer claim, and what is still unknown",{"id":687,"data":872,"type":544},{"text":873},"\u003Cstrong>Confirmed by NVIDIA:\u003C\u002Fstrong> RTX Spark is a Windows PC platform built around Blackwell RTX graphics and Grace CPUs; systems can provide up to 128 GB of unified memory; DLSS 5 and the RTX gaming stack are supported; Nemotron 3.5 Bolt E4B 4GB is available to developers; the model supports 64K context, tool use, configurable reasoning and game-state grounding.",{"id":691,"data":875,"type":544},{"text":876},"\u003Cstrong>Manufacturer benchmark claims:\u003C\u002Fstrong> NVIDIA reports roughly 40% higher average quality than its previous model on selected benchmarks, up to roughly 80% fewer output tokens versus peers, and an October DLSS 5 model that runs twice as fast as the September version while halving GPU overhead and reducing 4K VRAM use by 20%.",{"id":695,"data":878,"type":544},{"text":879},"\u003Cstrong>Still unknown from this announcement:\u003C\u002Fstrong> the real frame-time impact of simultaneous rendering, speech and character inference across different RTX Spark systems; independent measurements of NPC response latency under game load; how many commercial games will adopt Nemotron 3.5 Bolt; and how developers will balance local AI quality against deterministic gameplay and hardware requirements.",{"id":699,"data":881,"type":553},{"text":882,"level":47},"The Figure Rocks take",{"id":703,"data":884,"type":544},{"text":885},"The most important part of NVIDIA's October 27 announcement is not one benchmark or one AI NPC demo. It is the emerging idea of the gaming PC as a shared AI runtime. Neural graphics, speech, retrieval, reasoning and game logic increasingly compete and cooperate inside the same frame-time and memory envelope.",{"id":707,"data":887,"type":544},{"text":888},"If that architecture works under real load, local AI characters could become less dependent on cloud round trips and more tightly connected to live game state, while neural rendering continues to consume AI compute for the image itself. That is a meaningful change in how games are built: the question shifts from whether a game uses AI to which AI workloads deserve local resources, when they should run, and what authority each one receives.",{"id":711,"data":890,"type":553},{"text":891,"level":47},"Primary sources and scope",{"id":715,"data":893,"type":544},{"text":894},"This article is based primarily on NVIDIA's \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fnvidia-rtx-spark-powers-neural-rendering-and-ai-characters-in-games\u002F'>October 27, 2026 RTX Spark gaming announcement\u003C\u002Fa>, the \u003Ca href='https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fnemotron\u002FNVIDIA-Nemotron-3.5-Bolt-E4B-4GB\u002F'>Nemotron 3.5 Bolt E4B 4GB research release\u003C\u002Fa> published October 23, and NVIDIA's \u003Ca href='https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fbuild-on-device-ai-companions-with-the-nvidia-ace-game-agent-sdk-and-unreal-engine-5-plugins\u002F'>ACE Game Agent SDK documentation and examples\u003C\u002Fa>.",{"id":719,"data":896,"type":544},{"text":897},"Where NVIDIA provides performance or quality numbers, Figure Rocks treats them as vendor-reported measurements unless independent evidence is available. Product support, game adoption and runtime behavior can change as SDKs, drivers and game integrations evolve.","2.31.0","NVIDIA is bringing neural rendering and local AI character reasoning onto the same gaming platform. RTX Spark, DLSS 5 and Nemotron 3.5 Bolt show why the next challenge is not simply running AI in games, but making graphics, speech and agent inference coexist without breaking the experience.",{"lang":7,"title":534,"content":536,"contentJson":901,"excerpt":723},{"time":538,"blocks":902,"version":722},[903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991],{"id":541,"data":904,"type":544},{"text":543},{"id":546,"data":906,"type":544},{"text":548},{"id":550,"data":908,"type":553},{"text":552,"level":47},{"id":555,"data":910,"type":544},{"text":557},{"id":559,"data":912,"type":544},{"text":561},{"id":563,"data":914,"type":553},{"text":565,"level":47},{"id":567,"data":916,"type":544},{"text":569},{"id":571,"data":918,"type":544},{"text":573},{"id":575,"data":920,"type":544},{"text":577},{"id":579,"data":922,"type":553},{"text":581,"level":47},{"id":583,"data":924,"type":544},{"text":585},{"id":587,"data":926,"type":544},{"text":589},{"id":591,"data":928,"type":544},{"text":593},{"id":595,"data":930,"type":553},{"text":597,"level":47},{"id":599,"data":932,"type":544},{"text":601},{"id":603,"data":934,"type":544},{"text":605},{"id":607,"data":936,"type":544},{"text":609},{"id":611,"data":938,"type":544},{"text":613},{"id":615,"data":940,"type":544},{"text":617},{"id":619,"data":942,"type":553},{"text":621,"level":47},{"id":623,"data":944,"type":544},{"text":625},{"id":627,"data":946,"type":544},{"text":629},{"id":631,"data":948,"type":544},{"text":633},{"id":635,"data":950,"type":544},{"text":637},{"id":639,"data":952,"type":553},{"text":641,"level":47},{"id":643,"data":954,"type":544},{"text":645},{"id":647,"data":956,"type":544},{"text":649},{"id":651,"data":958,"type":544},{"text":653},{"id":655,"data":960,"type":553},{"text":657,"level":47},{"id":659,"data":962,"type":544},{"text":661},{"id":663,"data":964,"type":544},{"text":665},{"id":667,"data":966,"type":553},{"text":669,"level":47},{"id":671,"data":968,"type":544},{"text":673},{"id":675,"data":970,"type":544},{"text":677},{"id":679,"data":972,"type":544},{"text":681},{"id":683,"data":974,"type":553},{"text":685,"level":47},{"id":687,"data":976,"type":544},{"text":689},{"id":691,"data":978,"type":544},{"text":693},{"id":695,"data":980,"type":544},{"text":697},{"id":699,"data":982,"type":553},{"text":701,"level":47},{"id":703,"data":984,"type":544},{"text":705},{"id":707,"data":986,"type":544},{"text":709},{"id":711,"data":988,"type":553},{"text":713,"level":47},{"id":715,"data":990,"type":544},{"text":717},{"id":719,"data":992,"type":544},{"text":721},"Post erfolgreich abgerufen",{"items":995,"source":1068,"manualIds":1069,"manualMatchedIds":1070},[996,1002,1008,1014,1020,1026,1032,1038,1044,1050,1057,1062],{"id":997,"slug":998,"title":999,"excerpt":1000,"featuredImage":14,"publishedAt":1001},"226","mic-monitoring-side-tone-the-comfort-setting-that-prevents-shouting","麦克风监听（侧音）：防止大声喊叫的舒适设置","侧音功能能让您的声音保持自然，避免疲劳。正确设置侧音，可防止您在长时间通话时大声喊叫、过度紧绷下颌或分散注意力。","2026-02-20T22:00:00.000Z",{"id":1003,"slug":1004,"title":1005,"excerpt":1006,"featuredImage":14,"publishedAt":1007},"140","audio-eq-minimalism-small-changes-that-improve-footstep-readability","音频均衡极简主义：提升脚步声可辨性的细微调整","情商或许能提供帮助，但大幅度的曲线调整往往会破坏距离与方向感线索。应通过最小幅度的调整来优化脚步声效果，避免让音频变得模糊不清。","2026-02-20T21:30:00.000Z",{"id":1009,"slug":1010,"title":1011,"excerpt":1012,"featuredImage":14,"publishedAt":1013},"225","fix-input-lag-fast-pc-console-the-no-placebo-checklist","快速修复输入延迟（PC与主机）：非安慰剂检查清单","停止追逐虚幻的传说。这份清单直击沉重感的真实根源：显示处理、不稳定的节奏、渲染队列缓冲以及后台峰值。","2026-02-21T03:20:00.000Z",{"id":1015,"slug":1016,"title":1017,"excerpt":1018,"featuredImage":14,"publishedAt":1019},"262","stutter-fixes-that-actually-work-stop-chasing-random-graphics-tweaks","真正有效的口吃矫正方法：停止盲目追求图形调整","大多数口吃“矫正”方法之所以失败，是因为它们未能匹配口吃类型。请遵循这一实用步骤：先分类评估，再降低突发频率，稳定语速节奏，最后调整具体设置。","2026-02-21T03:00:00.000Z",{"id":1021,"slug":1022,"title":1023,"excerpt":1024,"featuredImage":14,"publishedAt":1025},"245","qos-myths-for-gaming-what-helps-what-hurts-and-the-real-priority","游戏中的QoS迷思：哪些有益，哪些有害，以及真正的优先级","QoS并非一个神奇的“游戏”开关。良好的队列管理能在负载下降低延迟，而糟糕的QoS则会增加抖动或破坏公平性。以下是理解这一概念的稳定思路。","2026-02-20T23:55:00.000Z",{"id":1027,"slug":1028,"title":1029,"excerpt":1030,"featuredImage":14,"publishedAt":1031},"247","input-lag-chain-deep-where-delay-builds-up-click-to-photon","输入延迟链深度：延迟累积之处（点击到光子）","输入延迟是一个链条，而非单一数字。了解从设备到显示器的延迟累积环节，以及能切实改善操作感（而非心理安慰）的优化步骤。","2026-02-21T00:10:00.000Z",{"id":1033,"slug":1034,"title":1035,"excerpt":1036,"featuredImage":14,"publishedAt":1037},"256","comfort-to-control-why-ergonomics-improves-aim-more-than-you-think","从舒适到掌控：为何人体工学对瞄准的提升远超你的想象","人体工学并非可有可无。疲劳会改变握持感、节奏与精准度。建立简单的舒适基准线，让你的操控数小时保持稳定如一。","2026-02-21T02:00:00.000Z",{"id":1039,"slug":1040,"title":1041,"excerpt":1042,"featuredImage":14,"publishedAt":1043},"248","ethernet-vs-wi-fi-for-gaming-the-honest-stability-tradeoff","以太网与Wi-Fi游戏对决：稳定性权衡的真相","速度并非主要问题，稳定性才是关键。以太网通常胜出，因为它能减少波动。参考本指南，判断何时Wi-Fi足够使用，何时则不然。","2026-02-21T05:20:00.000Z",{"id":1045,"slug":1046,"title":1047,"excerpt":1048,"featuredImage":14,"publishedAt":1049},"246","router-checklist-for-gaming-the-settings-that-actually-matter","游戏路由器设置清单：真正重要的配置项","大多数路由器调整并无助益。真正有效的设置包括：负载下的队列管理、稳定的Wi-Fi表现，以及避免增加延迟或不稳定性的功能。","2026-02-21T01:30:00.000Z",{"id":1051,"slug":1052,"title":1053,"excerpt":1054,"featuredImage":1055,"publishedAt":1056},"433","pre-order-alert-good-smile-company-figma-doom-the-dark-ages-doom-slayer-dx-edition","Pre-Order Alert: Good Smile Company Figma Doom: The Dark Ages – Doom Slayer DX Edition","The new Good Smile Company Figma Doom: The Dark Ages Doom Slayer DX Edition is more than a routine figure drop. It connects collector demand, franchise identity, and the wider appeal of Doom as one of gaming’s most durable icons.","\u002Fuploads\u002F2026\u002F05\u002Fpre-order-alert-good-smile-company-figma-doom-the-dark-ages-doom-slayer-dx-edition-1779227794098-251pwj.webp","2026-04-22T04:37:00.000Z",{"id":1058,"slug":1059,"title":1060,"excerpt":1061,"featuredImage":14,"publishedAt":1043},"244","network-test-under-load-the-only-result-that-predicts-gaming-feel","网络负载测试：唯一能预测游戏体验的结果","仅靠速度测试是不够的。游戏体验取决于负载下的延迟表现。采用这个简单的测试方法，可以揭示网络尖峰、抖动和缓冲区膨胀问题。",{"id":1063,"slug":1064,"title":1065,"excerpt":1066,"featuredImage":14,"publishedAt":1067},"273","router-placement-for-gaming-distance-and-obstacles-that-create-spikes","游戏路由器放置指南：导致延迟突增的距离与障碍物因素","在购置新路由器前，先优化环境布局。摆放位置、障碍物及信号干扰都会引发网络波动，导致延迟与卡顿现象。","2026-02-21T08:00:00.000Z","fallback",[],[]]