{"ok":true,"trend":{"id":792569,"platform":"mastodon","region":"global","key":"gpu 없이 소비자용 노트북에서 180억 파라미터 llm을 구동하는 pocket-darwin-180b. 4비트 gguf 양자화로 360gb→111gb 압축, 약 $1,400 하드웨어로 로컬 추론 가능. # ai #","title":"GPU 없이 소비자용 노트북에서 180억 파라미터 LLM을 구동하는 POCKET-Darwin-180B. 4비트 GGUF 양자화로 360GB→111GB 압축, 약 $1,400 하드웨어로 로컬 추론 가능. # ai #","url":"https://www.urbanmind.net/display/f7dd981d-35f5e1c7-acb70f28af5fe5fd","first_seen":"2026-10-02T23:50:08.242465Z","last_seen":"2026-10-02T23:53:07.010141Z","last_rank":1,"peak_rank":1,"last_volume":3,"peak_volume":3,"seen_count":1,"score":0.72015625,"category_hint":"software","section":"technology","category":"ai","summary":"A project called POCKET-Darwin-180B is drawing attention for running a 180-billion-parameter language model on consumer hardware with no discrete GPU. Using 4-bit GGUF quantization, the model is compressed from roughly 360GB down to 111GB, enabling local inference on hardware costing about $1,400. Commenters in AI and open-source circles are highlighting it as a sign that frontier-scale models may soon run off the cloud.","why":"Interest in running very large language models locally without expensive GPU hardware is growing, and this claims a striking compression result.","tone":"positive","entities":["POCKET-Darwin-180B","GGUF","Hackaday"],"summarized_at":"2026-10-02T23:51:25.103693Z","meta":{"tag":"opensource","via":"scan","kind":"status","lang":"ko","instance":"mastodon.social","tag_uses":894},"nw":null,"promo":null,"kind":null,"importance":null,"hidden":false,"hide_reason":null,"judged_at":null,"title_en":"180B-parameter LLM runs locally on a laptop without a GPU","section_name":"Technology","category_name":"AI","timeline":[{"captured_at":"2026-10-02T23:50:08.242465Z","rank":3,"volume":3},{"captured_at":"2026-10-02T23:53:07.010141Z","rank":1,"volume":3}],"posts":[{"platform":"mastodon","url":"https://www.urbanmind.net/display/f7dd981d-35f5e1c7-acb70f28af5fe5fd","author":"hackaday@www.urbanmind.net","title":null,"snippet":"GPU 없이 소비자용 노트북에서 180억 파라미터 LLM을 구동하는 POCKET-Darwin-180B. 4비트 GGUF 양자화로 360GB→111GB 압축, 약 $1,400 하드웨어로 로컬 추론 가능. # ai # machinelearning # opensource # llm # software # coding # development # engineering # inclusive # community Running a 180B-Parameter LLM on a Laptop Without a…","posted_at":"2026-10-02T23:01:15Z","likes":3}],"elsewhere":[],"window":"7d"}}