WINVIDIAIndependent RTX Spark index日本語

Guide & analysis · Nov 11, 2026

A Demo of Copilot Drafting a Repo Cleanup Plan With a Local Model — A Shrunken Coding AI, a One-Liter Box, and a Pen That Works on the Touchpad

A desk at night. A large violet block of light floats overhead and narrows into a small green crystal settling into a palm-sized black cube desktop. On the open laptop beside it, grey fragments drift off the screen like dust, leaving tidy glowing green lines. A pen rests by the keyboard. No text or logos.

In a demo Microsoft shared, once the user starts the task, GitHub Copilot audits the codebase for unused code, imports, dependencies and obsolete feature flags, investigates its findings across the whole repository, and comes back with a cleanup plan you can act on 1.

The model doing that work isn't in a data center. Microsoft's demo shows a low-bit model running locally on RTX Spark PCs 123. It's MAI-Code-1.1-Flash, a coding model with 137.9B parameters in a mixture-of-experts design 4.

Around RTX Spark, the "AI on your own desk" story moved in a few directions lately: a big coding model was squeezed down 5 and made available as a local model on RTX Spark 2, the box got smaller, and Lenovo put the pen on the touchpad too 6. Here they are in turn.

Shrinking 276 GB to 53.0 GiB

According to Microsoft's developer blog, quantization took the weights from roughly 276 GB at 16-bit precision down to 53.0 GiB, and a more compact 46.1 GiB variant was also built 5. The released 53.0 GiB checkpoint is available through Microsoft Foundry and as the local model in GitHub Copilot 7.

A smaller model is no use if it crawls, so the speed comes from a draft model: a small model proposes, the big one checks (speculative decoding). Microsoft says median decode throughput rose by 1.52 to 1.98 times across the input lengths it tested 8. At a 120K-token input, comparing the same model without and with the draft, median throughput went from 25.81 to 51.12 tokens per second, and median end-to-end latency fell from 527.25 to 382.41 seconds 9.

The conditions matter, so here they are. The test ran on an RTX Spark with 128 GB of unified memory and a 64 GB GPU allocation 10. Each request generated 8,192 tokens, with 3 repetitions per case and medians reported 11. With the draft model enabled, peak GPU memory stayed at or under 63.50 GB as the input grew 12. And Microsoft itself says these figures describe this specific setup and should not be generalized to different serving conditions 13. Read them as numbers for that configuration, exactly as the people who measured them intended.

A model file this big needs somewhere to live. If you plan to swap between several models, an external SSD makes life easier.

Why bother doing it locally

Microsoft states the aim plainly: bringing unmetered local intelligence to increasingly demanding coding workloads, without per-token cloud charges 14.

It isn't all-or-nothing, though. Cloud-scale models remain available when a task needs greater capability, so local and cloud complement each other 15. The next frontier, Microsoft writes, is local coding agents that respond faster and sustain longer coding trajectories within the same device budget 16.

The box shrinks too: GIGABYTE AI TOP AERO

The hardware side moved as well. On November 10, GIGABYTE announced AI TOP AERO, an AI desktop powered by the NVIDIA RTX Spark platform 17. Its compact chassis is approximately one liter 18.

According to GIGABYTE, inside is a 20-core Grace CPU paired with a Blackwell RTX GPU 19, up to 128 GB of unified memory 20, up to a 4 TB SSD 21, Windows 11 22, and 10GbE plus Wi-Fi 7 23. For regional configurations, pricing and availability, GIGABYTE points readers to its local announcements 24.

Hermitage Akihabara ran the news (in Japanese) under a headline about packing "RTX Spark" into a chassis of about 1 liter 25.

Lenovo's pen trick

Lenovo has 2 RTX Spark laptops in this story, and Lenovo Japan said of them that neither is positioned above the other 26.

PC Watch's headline (in Japanese) picked out the pen 27. On the convertible model, the bundled pen works not only on the display but on the haptic touchpad 6. Lenovo Japan explained, as reported by PC Watch (in Japanese), that drawing on the touchpad lets you see the whole screen while you work, and avoids the problem of your hand covering the display when you write on it directly 28.

Search on Amazon

Ad: the “Search on Amazon” buttons are affiliate links, and we may earn a commission. They open a search, not a specific listing.

The other is the Yoga Pro, which goes up to 128 GB of memory 29. At Lenovo Japan's product briefing, an Adobe Creative Cloud evangelist ran Premiere and Photoshop on it in a local environment with no network connection, PC Watch reports 30. The demo spotted power lines and cables in a landscape photo and removed them, and put text behind a person in a video 31. PC Watch also writes that Adobe's creative apps are optimized for RTX Spark and deliver up to 2 times faster performance 32.

Search on Amazon

Ad: the “Search on Amazon” buttons are affiliate links, and we may earn a commission. They open a search, not a specific listing.

Recap: what was shown at the November 2 briefing

AKIBA PC Hotline! published a visit report on NVIDIA's technical briefing.

According to AKIBA PC Hotline!, the briefing explained that the RTX Spark in laptops includes an NPU called "NV NPU" 33. The demos covered Hermes Agent editing in DaVinci Resolve without the user knowing the app's controls 34, task management across calendar, project tracking and email 35, and LTX 2.5 with RTX Video upscaling Full HD to 4K and expanding SDR to HDR 36. Marvel Rivals was shown as an example of a game with anti-cheat that supports Windows on Arm 37.

AKIBA PC Hotline! also notes a CUDA core count of 6,144, the same as the GeForce RTX 5070 38. The reporter adds that for absolute gaming performance, a gaming PC with a discrete GPU is likely to be ahead in many respects 39.

For the full briefing, see How NVIDIA described RTX Spark at the Tokyo event and How far can an RTX Spark laptop go for gaming?.

If you're choosing: start with memory

Microsoft's measurements were taken on a configuration with 128 GB of memory 10. The Yoga Pro goes up to 128 GB 29, and so does AI TOP AERO 20. Microsoft's blog does not name the machine it measured on, though. Memory differs by model and configuration, so if "a big coding AI on my own machine" is the goal, look at the memory first.

Before you buy, check the official support information for the tools you want to run.

Read next

On picking memory, see a deeper look at choosing memory. On how much to let a local agent touch, see How much should you let a local AI agent touch?. On working away from the wall socket, see Unplugged, a big local model still writes your code.

Sources

  1. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierAfter the user starts the task, Copilot audits the codebase for unused code, imports, dependencies, and obsolete feature flags, investigates findings across the repository, and produces an actionable cleanup plan, with the low-bit model running locally on RTX Spark PCs.
  2. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierBy making MAI-Code-1.1-Flash available as local model in GitHub Copilot on RTX Spark
  3. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency Frontierwith the low-bit model running locally on RTX Spark PCs.
  4. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierMAI-Code-1.1-Flash is a 137.9-billion-parameter mixture-of-experts model.
  5. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierQuantization reduced the weight footprint from roughly 276 GB at 16-bit precision to 53.0 GiB (3.31 bpw) , with a more compact 46.1 GiB (2.87 bpw) variant also developed.
  6. NVIDIA RTX Spark: タッチパッドでもペンが使える、RTX Spark搭載の2in1「Yoga 9n」 - PC WatchLenovo Yoga Pen Gen 2を付属。ディスプレイだけでなく、触覚タッチパッド上でもペンを利用できる。
  7. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierThe released 53.0 GiB checkpoint is available through Microsoft Foundry and as the local model in GitHub Copilot
  8. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierUnder this measured configuration, the draft increased median decode throughput by 1.52–1.98× across tested input lengths.
  9. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierAt 120K input, median throughput rose from 25.81 to 51.12 tokens/s , while median end-to-end latency fell 27% , from 527.25 to 382.41 seconds .
  10. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierOn RTX Spark ( 128 GB unified memory; 64 GB GPU allocation ), we compared the same Q2-XS target alone and with our DFlash2 draft across six input lengths from 1K to 120K tokens .
  11. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierEach request generated 8,192 tokens , with three repetitions per case; results report medians.
  12. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierWith layer-wise sliding-window attention, peak GPU memory in the draft-enabled configuration rose from 59.42 to just 63.50 GB as input grew from 1K to 120K tokens.
  13. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierThese figures describe this specific Q2-XS and DFlash2 setup and should not be generalized to different serving conditions.
  14. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierPowered by NVIDIA RTX Spark, we are bringing the promise of unmetered local intelligence to increasingly demanding coding workloads—giving developers greater freedom to experiment, delegate, and iterate on their own hardware, without per-token cloud charges.
  15. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierLow-bit inference creates room for more useful coding work close to a developer’s data and tools, while cloud-scale models remain available when tasks require greater capability.
  16. MAI-Code-1.1-Flash: Advancing the Quality-Efficiency Frontier for Coding AI on Windows PCs - Microsoft Foundry on Windows Blog Coding AI on Windows: The Quality–Efficiency FrontierThe next frontier is a new generation of local coding agents that respond faster, sustain longer coding trajectories, and take on increasingly capable work within the same device budget.
  17. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™TAIPEI, Nov. 10, 2026 /PRNewswire/ -- GIGABYTE today announced the launch of AI TOP AERO , a new AI desktop powered by the NVIDIA RTX Spark platform .
  18. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™GIGABYTE integrates its cooling design into AI TOP AERO's compact chassis of approximately one liter
  19. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™AI TOP AERO features the NVIDIA RTX Spark N1X Superchip , integrating a 20-core NVIDIA Grace CPU with an NVIDIA Blackwell RTX GPU .
  20. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™Configurations offer up to 128GB of LPDDR5x unified system memory and up to a 4TB PCIe Gen5 SSD
  21. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™Configurations offer up to 128GB of LPDDR5x unified system memory and up to a 4TB PCIe Gen5 SSD
  22. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™Featuring local AI and RTX-accelerated creation on Windows 11
  23. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™with USB Type-C, 10GbE Ethernet and Wi-Fi 7 connectivity for peripherals, data transfers and network access
  24. GIGABYTE AI TOP AERO: GIGABYTE Expands Its Local AI Portfolio with the Launch of AI TOP AERO Powered by NVIDIA RTX SPARK™GIGABYTE AI TOP AERO launches on November 10, 2026. Please refer to local GIGABYTE announcements for regional product configurations, pricing and availability.
  25. Post by @hermita_akiba約1リットルの筐体に「RTX Spark」を凝縮、GIGABYTE「AI TOP AERO」登場
  26. NVIDIA RTX Spark: タッチパッドでもペンが使える、RTX Spark搭載の2in1「Yoga 9n」 - PC Watch「どちらが上位という位置づけはなく、どのように使うかによって選択できる」と説明。
  27. Post by @pc_watchタッチパッドでもペンが使える、RTX Spark搭載の2in1「Yoga 9n」
  28. NVIDIA RTX Spark: タッチパッドでもペンが使える、RTX Spark搭載の2in1「Yoga 9n」 - PC Watch触覚タッチパッドでペンを利用すれば、画面全体を確認しながら作業ができる。ディスプレイに直接書き込むと手に隠れて見にくいといった課題も解決できる」などとした。
  29. Lenovo Yoga Pro 9n (15″, 11): Lenovo Expands the Yoga Portfolio with New AI PCs and Tablets Built for CreatorsUp to 128GB 256-bit 9400MT/s LPDDR5X, 16 channel
  30. NVIDIA RTX Spark: タッチパッドでもペンが使える、RTX Spark搭載の2in1「Yoga 9n」 - PC WatchLenovo Yoga Pro 9n Gen 11を使い、ネットに接続しないローカル環境でAdobe PremiereとAdobe Photoshopのデモンストレーションを行なった。
  31. NVIDIA RTX Spark: タッチパッドでもペンが使える、RTX Spark搭載の2in1「Yoga 9n」 - PC WatchAdobe PhotoshopではAIベースの削除ツールを使って風景写真から電線とケーブルを検出して削除し、Adobe Premiereでは動画の被写体の女性の後ろに文字を表示するといった編集作業を、簡単に行なってみせた。
  32. NVIDIA RTX Spark: タッチパッドでもペンが使える、RTX Spark搭載の2in1「Yoga 9n」 - PC Watchアドビのクリエイティブアプリは、NVIDIA RTX Spark向けに最適化されており、最大2倍の高速化を実現しているという。
  33. NVIDIA RTX Spark: RTX Sparkは何ができるPCなのか、AIエージェントやニューラルレンダリングゲームのデモなどNVIDIAが技術説明会を開催 - AKIBA PC Hotline!DGX SparkとRTX Sparkはチップ自体はかなり近いものの、ノートPCに採用されるRTX SparkにはNPUの「NV NPU」が搭載されているといったハードウェア面の解説も。
  34. NVIDIA RTX Spark: RTX Sparkは何ができるPCなのか、AIエージェントやニューラルレンダリングゲームのデモなどNVIDIAが技術説明会を開催 - AKIBA PC Hotline!Hermes Agentに指示を出すことで、DaVinci Resolveの操作が分からなくても本格的な動画編集が可能。
  35. NVIDIA RTX Spark: RTX Sparkは何ができるPCなのか、AIエージェントやニューラルレンダリングゲームのデモなどNVIDIAが技術説明会を開催 - AKIBA PC Hotline!カレンダーや進行管理、メールなど、複数のアプリを横断して状況を把握し、個人やチームのタスク管理が手物のPCで行えることを実演。
  36. NVIDIA RTX Spark: RTX Sparkは何ができるPCなのか、AIエージェントやニューラルレンダリングゲームのデモなどNVIDIAが技術説明会を開催 - AKIBA PC Hotline!フルHDから4Kへのアップスケーリングや、SDRからHDRへのダイナミックレンジ拡大処理など、搭載しているGPUがGeForceだからこそ行える活用方法が紹介されました。
  37. NVIDIA RTX Spark: RTX Sparkは何ができるPCなのか、AIエージェントやニューラルレンダリングゲームのデモなどNVIDIAが技術説明会を開催 - AKIBA PC Hotline!Arm版Windowsに対応したアンチチート機能の実装するゲームも増えつつあり、快適に動作する例として「Marvel Rivals」が紹介されていました。
  38. NVIDIA RTX Spark: RTX Sparkは何ができるPCなのか、AIエージェントやニューラルレンダリングゲームのデモなどNVIDIAが技術説明会を開催 - AKIBA PC Hotline!CUDAコアもGeForce RTX 5070と同じ6,144基で、最新ゲームも快適に遊べる性能を持っている点も特徴となっています。
  39. NVIDIA RTX Spark: RTX Sparkは何ができるPCなのか、AIエージェントやニューラルレンダリングゲームのデモなどNVIDIAが技術説明会を開催 - AKIBA PC Hotline!絶対的なゲーム性能に関しては、単体のディスクリートGPUを搭載するゲーミングPCなどの方が高性能となる面も多々あると思われますが

Embedded posts belong to their authors. Ad: the “Search on Amazon” buttons are affiliate links, and we may earn a commission. They open a search, not a specific listing.