NVIDIA RTX Spark能为开发者，创造者和游戏者所做的一切所建造的薄而轻的笔记本电脑。
RTX Spark笔记本电脑现在可以从ASUS、Dell、HP、Lenovo、Microsoft和MSI获得。 这些强大的系统将NVIDIA Blackwell RTX GPU和NVIDIA Grace CPU合并在一个单一的超级芯片中，并有高达128GB的统一内存和高达1个petaflop的FP4 AI性能。 这使得NVIDIA CUDA平台，RTX图形以及个人AI超级计算机的能力在高价的Windows笔记本电脑内被建造到任何地方。
即将推出的新的和预期的RTX Spark更新包括：
- NVIDIA 尼莫特龙3.5 RTX Spark上提供转写、演讲者归属和翻译的开放式语重模型。
- LFM3的开放型号家族，日零支持。
- NVIDIA App中的资源管理控制，在前地应用和背景agents之间分配GPU资源。
-"幽灵之刃"(Phantom Blade Zero),S-GAME的极受期待的动作角色扮演游戏，有射线追踪功能的发布和NVIDIA DLSS 4.5.
- Minecraft在路径追踪方面的经验，DLSS在RTX Remix1.6中，现在可供RTX Spark使用。
以 NVIDIA Nemotron 3.5 转录录音音频到有用的信息
推出今天，NVIDIA尼莫特龙3.5 Transis是一个新的开放重量的语音模型，将被录制的对话转化为有用的信息。 开发人员不用需要多个模型来进行抄写，扬声器标签和翻译，而是可以使用一个能处理所有三个的快速模型，加上关于音频的问题。 它转录了40种语言，包括7种印地语。
开发者用平话提示来指导模型。 例如，对于一次有记录的会议，用户可以要求其：
- “记录和标出每个发言者的录音”。
- “将这一音频翻译成英文。”
- “列出本次会议所作的决定。”
提示还可以包括产品术语和格式化惯例，这有助于模型处理保健、金融服务和客户服务等领域的专门词汇。 由于权重是开放的，开发者可以选择音频处理的地方，从桌面到云。
尼莫特龙 3.5 Trancis将Hugging Face Open ASR和2号排在人工分析开口重量模型中——以约43亿活性参数提供领先精度，比一号开口重量模型少了80%，使得高质量，智能的抄写在本地硬件上更加实用。
它今天以BF16,FP8和NVFP4格式在Hugging Face上提供，并在NVIDIA RTX Spark和DGX Spark系统，Jetson AGX Thor设备以及GeForce RTX 5090 GPU上提供支持，为开发者提供灵活的部署选项。 开发者可以通过NeMo-Speech.cpp或vLLLM部署NVFP4版本。
NVIDIA技术博客更多学习。
控制 Agents 和 PC Apps 共享 GPU 资源
在RTX Spark上，用户可以让长期运行的agents与其最喜爱的应用程序一起工作。 两者都分享系统的GPU计算，资源的适当平衡取决于此时用户的要害。
有了NVIDIA App中的新资源管理功能，用户现在可以选择如何共享GPU资源。 他们可以为最佳性能而优先排列他们的前缘应用，或者给他们背景运行的agent提供更多资源来更快地完成工作。
从 System > 在 NVIDIA App 中高级访问控制资源共享。 这个功能需要硬件加速的GPU调度在Windows设置中启用。
液态AI：一个模范家庭，多种工作方式
液态AI的LFM3提供了新一代液态基础模型，为专门任务所设计。 家庭跨越文本、视觉、音频、OMNI和决定模型，以一个共享的主干为基础，基础模型和训练后模型为开放权重。 这些模型是紧凑而快的：液态AI新的17亿参数基模型超越了之前的26亿参数基模型。
这些模型支持在赫尔梅斯Agent，皮和OpenClaw运行的agents等本地工作流程，用于分解收件箱并管理日历，阅读文档和应用程序屏幕，翻译和翻译语音，回答手写数学的口述问题，以及路由支持票或语音请求。
开发者可以在RTX Spark上通过llama.cpp和vLLLM运行LFM3模型，并在本地运行这些模型。
发布带DLSS 4.5
S -GAME的幽灵之刃零发布今晚10月28日下午7点在Steam和Epic Games Store上玩家可以扮演"灵魂"的角色，他是一位剑客被陷害于他主人被谋杀，他旅行到武道世界去揭发阴谋。
NVIDIA与S-GAME Studio和S-GAME Publishing合作，将射线跟踪效果加入标题。 在RTX Spark笔记本电脑和GeForce RTX GPU动力PC上，射线追踪新增更精确地弹出照明，详细反射和对叶片和地形的现实阴影。 NVIDIA DLSS动态多帧生成功能能以6x帧生成来提升帧率，或调整苍蝇上乘以击出玩家的目标帧率。
详见于GeForce.com.
RTX Remix 呼吸新生命入经典
NVIDIA RTX Remix 以路径追踪和DLSS重制经典游戏的moding平台发布上星期的1.6版本。 这一更新将RTX Remix带入了世界上最大的游戏界：Minecraft. 创作者和玩家都可以通过RTX Remix来制作Minecraft Java版1.21.1并使用DLSS加速路径追踪，并在未来的创作中充分利用现实的照明和材料。
更新内容还用3D-Guided Neural Rendering的新增 DLSS 5，可达6x多帧生成，原生RTX Spark支持和agent辅助工作流程。 从今天开始，这些升级会随着RTX和"半生2"RTX演示来到门户网站。 两者现在都支持RTX Spark，其中DLSS 3D-Guided Neural Referming用于更多的生活类照明和材料，DLSS框架生成的新性能模式和加快路径追踪的新选项。
RTX Remix 1.6也使AI动力摩丁更简单。 一个被重新设计的ComfyUI工作流程让moders直接在RTX Remix内部生成以物理为基础的材料，没有应用编程接口设置，批量处理用于完整的项目，并为技术较少的创造者预设。 此外，有NVIDIA agent技能，相容的AI agents可以直接与RTX Remix一起工作来帮助加速重做项目。
在RTX Remix博客中学习更多。
RTX Spark 笔记本电脑：设计精美，万事通
RTX Spark笔记本电脑出现了一系列的设计，因此用户可以选择一个适合他们工作与演奏的方式。 选项包括不同的屏幕大小，颜色，触摸屏，笔支持和二进制敞篷。 RTX Spark笔记本电脑有14毫米的薄度和3磅的轻度，全天电池寿命。
由于RTX Spark将GPU,CPU和高达128GB的统一内存放入一款功率高效的超芯片上，所以这种微弱的设计是可能的。 Creative projects and AI models 从同一个内存池中抽取出，所以一台笔记本电脑可以承担以前调用桌面工作站的工作，即使没有插出。
以下是这意味着：
- AI开发者：在NVIDIA CUDA上本地运行模型和agents——在云中赋予AI权力的同一平台——在云中部署超过1.5亿个NVIDIA RTX AI PC和NVIDIA GPU的路径。
- 创建者：RTX Spark可以编辑原生相机4:2:2视频并渲染出可达90GB的3D场景。 Adobe Photoshop和Premee通过β 发布提供本土的RTX Spark支持。
- Gamers：在RTX Spark上跑出上百个游戏，由NVIDIA DLSS，射线追踪，Reflex和G-SYNC提供更锋利的视觉和更平滑更能响应的游戏播放。
RTX Spark笔记本电脑现在可以从ASUS,Dell,HP,Lenovo,Microsoft和MSI获得，从2,599美元开始，有128GB的配置在货架上。 在RTX Spark产品页面上找到笔记本电脑。
#ICYMI：更多来自NVIDIA本地AI的更新
Microducks从RTX Spark学习行走：在GTC柏林主题演讲期间，NVIDIA创始人和CEOJensen Huang展示了在RTX Spark上运行的AI agents如何能帮助训练Hugging Face的Microduck机器人。 一个新的NVIDIA技术博客走遍了工作流程：赫尔梅斯·Agent和尼莫特隆·3.5·博尔特计划了RTX Spark上的障碍课程，Astra建设了3D资产，NVIDIA Isaac Lab训练了导航政策，而RTX Spark在NVIDIA Isaac Sim中验证了它。 观看演示并试玩本。
NVIDIA 尼莫特龙 3.5 博尔特 E4B 4GB 现在已经可以使用，可以进行自然对话并多步agent任务，但内存小到4GB. 该模型在RTX Spark,DGX Spark,GeForce RTX GPUs和NVIDIA Jetson设备上赋予了本地语音助理，游戏角色和嵌入式接口。 它支持llama.cpp,vLLM,Ollama,Unsloth和LM Studio，并与Hermes和OpenClaw合作。 对于要求更高的agent工作量，Nemotron 3.5 Bolt 74B-A9B 24GB设计在RTX Spark上运行本地agents.
Black Forest Labs的FLUX 3 Image Klein是一个56亿参数的开放权重模型，让用户在当地生成并编辑图像。 NVIDIA-优化版本运行于RTX GPU上，其VRAM的版本还不到8GB. 开发者还可以使用NVIDIA NeMo AutoModel 配方来自定义用于特定创意工作流程的RTX Spark上的模型。
NVIDIA DGX Spark 64GB现在可以向制造商伙伴购买，为开发者和研究人员提供了另一种在当地建立和运行AI的方法。 由GB10 Grace Blackwell Superchip提供动力，将64GB的统一内存与DGX OS和NVIDIA AI软件堆叠结合，用于agent开发，推论和微调。 学习更多，探索购买方案。
追踪在X,Instagram,TikTok和Facebook上的NVIDIA RTX Spark——通过订阅NVIDIA本地AI通讯随时了解情况。 跟随NVIDIA工作站在LinkedIn和X上。
见关于软件产品信息的通知。
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
NVIDIA RTX Spark powers thin and light laptops built for everything that developers, creators and gamers do.
RTX Spark laptops are now available from ASUS, Dell, HP, Lenovo, Microsoft and MSI. These powerful systems combine an NVIDIA Blackwell RTX GPU and an NVIDIA Grace CPU in a single superchip with up to 128GB of unified memory and up to 1 petaflop of FP4 AI performance. That puts the NVIDIA CUDA platform, RTX graphics and the capabilities of a personal AI supercomputer inside premium Windows laptops built to go anywhere.
New and expected RTX Spark updates, coming soon, include:
- NVIDIA Nemotron 3.5 Transcribe, an open weight speech model for transcription, speaker attribution and translation is available on RTX Spark.
- The LFM3 family of open models with day-zero support.
- Resource management controls in NVIDIA App to allocate GPU resources between foreground apps and background agents.
- Phantom Blade Zero, S-GAME’s highly-anticipated action role-playing game, launches with ray tracing and NVIDIA DLSS 4.5.
- Experience Minecraft with path tracing and DLSS with RTX Remix1.6, available now for RTX Spark.
Turn Recorded Audio Into Useful Information With NVIDIA Nemotron 3.5 Transcribe
Introduced today, NVIDIA Nemotron 3.5 Transcribe is a new, open weight speech model that turns recorded conversations into useful information. Instead of needing multiple models for transcription, speaker labels and translation, developers can use one promptable model that handles all three, plus questions about the audio. It transcribes 40 languages, including seven Indic languages.
Developers guide the model with plain-language prompts. For example, for a single recorded meeting, users can ask it to:
- “Transcribe this recording and label each speaker.”
- “Translate this audio into English.”
- “List what decisions were made in this meeting.”
Prompts can also include product terms and formatting conventions, which helps the model handle specialized vocabulary in fields like healthcare, financial services and customer service. Because the weights are open, developers can choose where audio is processed, from a desktop to the cloud.
Nemotron 3.5 Transcribe ranks No. 1 on the Hugging Face Open ASR and No. 2 among open weight models on Artificial Analysis — delivering leading accuracy with approximately 4.3 billion active parameters, 80% fewer than the No. 1 open weight model, making high-quality, intelligent transcription more practical on local hardware.
It’s available today on Hugging Face in the BF16, FP8 and NVFP4 formats, and offers flexible deployment options for developers with support on NVIDIA RTX Spark and DGX Spark systems, Jetson AGX Thor devices and GeForce RTX 5090 GPUs. Developers can deploy NVFP4 versions through NeMo-Speech.cpp or vLLM.
Learn more in the NVIDIA technical blog.
Control How Agents and PC Apps Share GPU Resources
On RTX Spark, users can have long-running agents working alongside their favorite applications. Both share the system’s GPU compute, and the right balance of resources depends on what matters to users at that moment.
With the new resource management feature in NVIDIA App, users can now choose how GPU resources are shared. They can prioritize their foreground app for the best performance, or give their background-running agent more resources to get work done faster.
Access control resource sharing from System > Advanced in the NVIDIA App. This feature requires hardware-accelerated GPU scheduling to be enabled in Windows Settings.
Liquid AI: One Model Family, Many Ways to Work
Liquid AI’s LFM3 provides a new generation of Liquid Foundation Models designed for specialized tasks. The family spans text, vision, audio, omni and decision models built on one shared backbone, with base and post-trained models available as open weights. The models are compact and fast: Liquid AI’s new 1.7-billion-parameter base model outperforms its previous 2.6-billion-parameter base model.
These models support local workflows such as agents running in Hermes Agent, Pi and OpenClaw to triage inboxes and manage calendars, read documents and app screens, transcribe and translate speech, answer spoken questions about handwritten math, and route support tickets or voice requests.
Developers can run LFM3 models on RTX Spark with native support through llama.cpp and vLLM, and fine-tune the models locally.
‘Phantom Blade Zero’ Launches With DLSS 4.5
S-GAME’s Phantom Blade Zero launches tonight, Oct. 28, at 7 p.m. PT on Steam and the Epic Games Store. Players can take on the role of Soul, a swordsman framed for his master’s murder, as he travels the martial world to uncover a conspiracy.
NVIDIA worked with S-GAME Studio and S-GAME Publishing to add ray-traced effects to the title. On RTX Spark laptops and GeForce RTX GPU-powered PCs, ray tracing adds more accurate bounced lighting, detailed reflections and realistic shadows on foliage and terrain. The NVIDIA DLSS Dynamic Multi Frame Generation feature boosts frame rates with up to 6x frame generation, or adjusts the multiplier on the fly to hit a player’s target frame rate.
Read more on GeForce.com.
RTX Remix Breathes New Life Into Classics
NVIDIA RTX Remix, the modding platform for remastering classic games with path tracing and DLSS, released version 1.6 last week. This update brought RTX Remix to the world’s largest gaming community: Minecraft. Both creators and players can render Minecraft Java Edition 1.21.1 through RTX Remix with DLSS-accelerated path tracing and take full advantage of realistic lighting and materials in their future creations.
The update also adds DLSS 5 with 3D-Guided Neural Rendering, up to 6x Multi Frame Generation, native RTX Spark support and agent-assisted workflows. Starting today, those upgrades come to Portal with RTX and the Half-Life 2 RTX demo. Both now support RTX Spark, with DLSS 3D-Guided Neural Rendering for more lifelike lighting and materials, a new Performance Mode for DLSS Frame Generation and new options that speed up path tracing.
RTX Remix 1.6 also makes AI-powered modding simpler. A redesigned ComfyUI workflow lets modders generate physically based materials directly inside RTX Remix, with no application programming interface setup, batch processing for full projects and presets for less technical creators. Plus, with NVIDIA agent skills, compatible AI agents can work directly with RTX Remix to help speed up remastering projects.
Learn more in the RTX Remix blog.
RTX Spark Laptops: Beautifully Designed, Built for Everything
RTX Spark laptops come in a range of designs, so users can choose one that fits how they work and play. Options include different screen sizes, colors, touchscreens, pen support and two-in-one convertibles. RTX Spark laptops are as thin as 14mm and as light as three pounds, with all-day battery life.
Such slim designs are possible because RTX Spark places the GPU, CPU and up to 128GB of unified memory on one power-efficient superchip. Creative projects and AI models draw from the same memory pool, so a laptop can take on work that used to call for a desktop workstation, even when unplugged.
Here’s what this means for:
- AI developers: Run models and agents locally on NVIDIA CUDA — the same platform that powers AI in the cloud — with a path to deploy across more than 150 million NVIDIA RTX AI PCs and NVIDIA GPUs in the cloud.
- Creators: RTX Spark can edit camera native 4:2:2 video and render 3D scenes of up to 90GB. Adobe Photoshop and Premiere offer native RTX Spark support through beta releases.
- Gamers: Hundreds of games run on RTX Spark, with NVIDIA DLSS, ray tracing, Reflex and G-SYNC delivering sharper visuals and smoother, more responsive gameplay.
RTX Spark laptops are available now from ASUS, Dell, HP, Lenovo, Microsoft and MSI, starting at $2,599, with 128GB configurations on shelves. Find a laptop on the RTX Spark product page.
#ICYMI: More Updates From NVIDIA Local AI
🦆Microducks learn to walk with help from RTX Spark: During the GTC Berlin keynote, NVIDIA founder and CEO Jensen Huang showed how AI agents running on RTX Spark can help train Hugging Face’s Microduck robot. A new NVIDIA technical blog walks through the workflow: Hermes Agent and Nemotron 3.5 Bolt plan an obstacle course on RTX Spark, Astra builds the 3D assets, NVIDIA Isaac Lab trains the navigation policy and RTX Spark validates it in NVIDIA Isaac Sim. Watch the demo and try the playbook.
⚡NVIDIA Nemotron 3.5 Bolt E4B 4GB is now available, enabling natural conversations and multistep agent tasks with as little as 4GB of memory. The model powers local voice assistants, game characters and embedded interfaces on RTX Spark, DGX Spark, GeForce RTX GPUs and NVIDIA Jetson devices. It supports llama.cpp, vLLM, Ollama, Unsloth and LM Studio, and works with Hermes and OpenClaw. For more demanding agent workloads, Nemotron 3.5 Bolt 74B-A9B 24GB is designed to run local agents on RTX Spark.
🖼️Black Forest Labs’ FLUX 3 Image Klein is a 5.6-billion-parameter open weights model that lets users generate and edit images locally. NVIDIA-optimized versions run on RTX GPUs with as little as 8GB of VRAM. Developers can also fine-tune the model on RTX Spark using an NVIDIA NeMo AutoModel recipe to customize it for specific creative workflows.
🖥️NVIDIA DGX Spark 64GB is now available to purchase from manufacturer partners, giving developers and researchers another way to build and run AI locally. Powered by the GB10 Grace Blackwell Superchip, it combines 64GB of unified memory with DGX OS and the NVIDIA AI software stack for agent development, inference and fine-tuning. Learn more and explore purchase options.
Follow NVIDIA RTX Spark on X, Instagram, TikTok and Facebook — and stay informed by subscribing to the NVIDIA Local AI newsletter. Follow NVIDIA Workstation on LinkedIn and X.
See notice regarding software product information.
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.