Sudo su (@sudoingX)로컬 AI를 여러 GPU 등급에서 실험한 결과, Qwen 3.5 9B를 RTX 3060 12GB에서 128K 컨텍스트와 초당 50토큰으로 구동해 단일 프롬프트로 전체 게임을 자율적으로 만들었다는 사례를 공유했다. 엔트리급 GPU에서도 강력한 로컬 AI 활용 가능성을 보여준다.https://x.com/sudoingX/status/2050984488063422887#localai #qwen #gpu #llm #agents
Related
China's Ministry of Commerce accused US AI firms of distilling Chinese models Monday, promised countermeasures if Washin...
China's Ministry of Commerce accused US AI firms of distilling Chinese models Monday, promised countermeasures if Washington sanctions Chinese companies. It named no firms and prov...
#NVIDIA and founding members form new Open Secure #AI Alliance https://www.elevenforum.com/t/nvidia-and-founding-members...
#NVIDIA and founding members form new Open Secure #AI Alliance https://www.elevenforum.com/t/nvidia-and-founding-members-form-new-open-secure-ai-alliance.48368/
公取委の話、多いですね外部販売ルール緩和、アップルとグーグルが方針転換 公取委確認 https://mainichi.jp/articles/20260727/k00/00m/020/325000c#Apple #LLM #news #bo...
公取委の話、多いですね外部販売ルール緩和、アップルとグーグルが方針転換 公取委確認 https://mainichi.jp/articles/20260727/k00/00m/020/325000c#Apple #LLM #news #bot