{"ok":true,"trend":{"id":1293580,"platform":"mastodon","region":"global","key":"vidraft의 pocket-darwin-180b-gguf로 180b 파라미터 moe 모델을 8gb vram 노트북에서 구동. 4비트 양자화와 llama.cpp로 250배 하드웨어 요구사항 절감, 로컬 ai 배포 완","title":"VIDRAFT의 POCKET-Darwin-180B-GGUF로 180B 파라미터 MoE 모델을 8GB VRAM 노트북에서 구동. 4비트 양자화와 llama.cpp로 250배 하드웨어 요구사항 절감, 로컬 AI 배포 완","url":"https://www.urbanmind.net/display/f7dd981d-ca1c6d6b-0a4a469a2351e31b","first_seen":"2026-10-06T23:52:50.147256Z","last_seen":"2026-10-07T01:14:47.640428Z","last_rank":4,"peak_rank":4,"last_volume":3,"peak_volume":3,"seen_count":2,"score":0.566640625,"category_hint":"software","section":"technology","category":"software","summary":"VIDRAFT has released POCKET-Darwin-180B-GGUF, a quantized build that reportedly runs a 180-billion-parameter mixture-of-experts model on a laptop with just 8GB of VRAM. Using 4-bit quantization and llama.cpp, the project claims hardware requirements are cut by roughly 250 times, making local deployment of very large AI models feasible on consumer machines.","why":"Running a 180B-parameter model on modest consumer hardware is a striking claim that excites the local AI and open-source community.","tone":"neutral","entities":["VIDRAFT","POCKET-Darwin-180B-GGUF","llama.cpp"],"summarized_at":"2026-10-06T23:53:06.945574Z","meta":{"tag":"opensource","via":"scan","kind":"status","lang":"en","instance":"mastodon.social","tag_uses":540},"nw":null,"promo":null,"kind":null,"importance":null,"hidden":false,"hide_reason":null,"judged_at":null,"title_en":"180B-Parameter AI Model Claims to Run on 8GB Laptop GPU","section_name":"Technology","category_name":"Software","timeline":[{"captured_at":"2026-10-06T23:52:50.147256Z","rank":5,"volume":3},{"captured_at":"2026-10-07T01:14:47.640428Z","rank":4,"volume":3}],"posts":[{"platform":"mastodon","url":"https://www.urbanmind.net/display/f7dd981d-ca1c6d6b-0a4a469a2351e31b","author":"hackaday@www.urbanmind.net","title":null,"snippet":"VIDRAFT의 POCKET-Darwin-180B-GGUF로 180B 파라미터 MoE 모델을 8GB VRAM 노트북에서 구동. 4비트 양자화와 llama.cpp로 250배 하드웨어 요구사항 절감, 로컬 AI 배포 완벽 가이드. # ai # machinelearning # opensource # llm # software # coding # development # engineering # inclusive # community Running a 180B-Parameter MoE Model on…","posted_at":"2026-10-06T23:01:29Z","likes":3}],"elsewhere":[],"window":"7d"}}