{"rewrite":{"id":"r_c79e5efd9ede74e4ab52a654","clusterId":"c_7539b42fb091a4b42a8500d8","slug":"mouse-computer-shows-96gb-vram-allocation-for-local-llms-at-tgs2026","model":"deepseek-v4-1-flash","headline":"Mouse Computer Shows 96GB VRAM Allocation For Local LLMs At TGS2026","summary":"At Tokyo Game Show 2026, Kiyoshi Shin of Barin Studio and Mouse Computer product manager Nami Hayashida presented a talk on running local LLMs in game development. The demo machine was Mouse Computer's DAIV CX, built on an AMD Ryzen AI Max+ processor with Radeon 8060S graphics, which can allocate up to 96GB of its 128GB unified memory as VRAM. Shin cited leak risk and API costs as reasons to run models locally.","whyItMatters":"The pitch treats memory allocation, not compute, as the practical gate on running the 70B to 80B class models developers want for long-context work, which is why a machine that turns main memory into VRAM is the demo rather than the software.","webCardHtml":"\u003cp\u003eThe argument on stage was narrower than a case for AI in general. Shin framed the choice between cloud and local as one of control: unpublished planning documents, setting bibles, character backstories and source code cannot be sent to an outside server without legal and security review, and pay-per-use API billing plus rate limits discourage the repeated prompting that development work involves.\u003c/p\u003e\u003cp\u003eHe conceded that a single PC runs slower than a data center, and pointed to Ollama and LM Studio as tools that make open models easy to run. The hardware on the booth is what he put behind the claim. Mouse Computer\u0026#39;s DAIV CX allocates up to 96GB of its 128GB unified memory as VRAM; typical graphics cards hold 16GB to 24GB. That ceiling decides how large a model and how long a context can be held in memory.\u003c/p\u003e","blueskyPost":"Mouse Computer's DAIV CX can hand 96GB of its 128GB unified memory to the GPU. For game teams, that reframes the buy: it is not a graphics card question, it is a system memory question.","twitterPost":"Mouse Computer's DAIV CX can assign 96GB of unified memory as VRAM, so the local-LLM purchase becomes a memory question, not a GPU one.","threadsPost":"Mouse Computer's DAIV CX can allocate 96GB of its 128GB unified memory as VRAM. That is the detail game teams will weigh, because running LLMs locally is a memory question before it is a graphics question. Kiyoshi Shin's case for it rests on leak risk and API costs.","newsletterBlurb":"Tokyo Game Show 2026 hosted a Mouse Computer stage where Kiyoshi Shin made the case for running large language models locally in game development, pointing to information leakage risk and API cost limits as the problems. The demo unit was the DAIV CX, which can allocate up to 96GB of its 128GB unified memory as VRAM. Shin said that capacity is what decides how large a model and how long a context can run on a single machine.","attributionJson":"[{\"source\":\"ASCII.jp\",\"url\":\"https://ascii.jp/elem/000/004/436/4436507/?rss\",\"title\":\"The Necessity of Bringing 'Local LLMs' into Game Development? The AI-Focused 'DAIV' That Turns 96GB of Main Memory into VRAM Shows a PC Transformation [TGS2026 Special]\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":4680,"outputTokens":731,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1789817362,"createdAt":"2026-09-19T11:23:42.000Z","publishedAt":"2026-09-19T11:28:20.000Z","updatedAt":"2026-09-19T11:28:20.000Z"},"cluster":{"id":"c_7539b42fb091a4b42a8500d8","canonicalTitle":"ゲーム開発に「ローカルLLM」を取り込む必然性とは？ メインメモリーの96GBをVRAM化するAI特化「DAIV」が示すPCの変革【TGS2026特集】","representativeArticleId":"a_2889b0f5743fbac4bd88cd00","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"DAIV\"],\"studios\":[],\"people\":[\"Kiyoshi Shin\"],\"type\":\"news\",\"domain\":\"games\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-09-19T10:30:00.000Z","lastSeenAt":"2026-09-19T10:30:00.000Z","updatedAt":"2026-09-19T11:28:20.000Z"},"attribution":[{"source":"ASCII.jp","url":"https://ascii.jp/elem/000/004/436/4436507/?rss","title":"ゲーム開発に「ローカルLLM」を取り込む必然性とは？ メインメモリーの96GBをVRAM化するAI特化「DAIV」が示すPCの変革【TGS2026特集】"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["DAIV"],"studios":[],"people":["Kiyoshi Shin"],"type":"news","domain":"games","is_roundup":false},"keyFacts":null}