{"id":1255,"kind":"story","title":"Open source claims to run a 284 billion-parameter DeepSeek model on a PC with 64GB memory without a GPU","url":"https://github.com/synchopate/llama-modchip","host":"github.com","by":"startupxo","score":0,"comments":1,"editorial_comments":1,"time":"2026-11-08T18:24:03.594Z","origin":"curated","language":{"source":"ko","reading":"en","translated":true},"summary":["llama-modchip, released by developer synchopate, is open source software (Apache-2.0) that compresses AI models further and adjusts CPU computation to let people run large AI models locally without a graphics card.","According to the developer, DeepSeek V4 Flash shrinks from 76.87GiB to 56.56GiB, and peak memory use is about 57.6GiB even with a 256K context, so it fits on a 64GB PC. The original text says the existing 76.87GiB version stops due to insufficient memory on 64GB Linux.","README figures show input processing at about 44tok/s and response generation at 9.06~10.74tok/s on an AMD Ryzen 9 9955HX (16 cores, 64GB DDR5). With an auxiliary draft technique, it reaches 11.5~14.7tok/s. These are the developer's own measurements.","Nemotron 3.5 30B at the 30 billion scale was reportedly reduced to 14.35GiB and achieved 25~60tok/s on a PC with 16~32GB memory. The compressed models use a proprietary format and cannot be opened in standard llama.cpp, Ollama or LM Studio."],"discussion":"https://startupxo.com/en/1255/","markdown":"https://startupxo.com/en/1255.md","api":"https://startupxo.com/api/v1/item.json?id=1255&lang=en","text":null,"edited":null,"sources":[{"site":"hn","name":"Hacker News","url":"https://news.ycombinator.com/item?id=50411961","score":237,"comments":72,"observed_at":"2026-11-08T18:22:59Z"}],"thread":[{"id":528,"by":"startupxo","score":0,"time":"2026-11-08T18:24:03.594Z","text":"O: 64GB For developers who want to try a large model on a desktop without a GPU, the suggestion is to run the CPU check script in the README, then start by measuring the speed of the 14.35GiB 30B model.\nX: The compressed model uses the dedicated GGML_TYPE_Q2_0 format, so it cannot be opened in standard llama.cpp, Ollama, or LM Studio. It must be run using the provided dedicated binary or the modchip command.","editorial":true,"replies":[]}]}