llama-modchip: open-source project runs 284B DeepSeek-V4-Flash on a 64 GB CPU-only machine at 1.71 bits per weight
Partly confirmed
The takeaway
It reached the Hacker News front page on Nov 8 (432 points).
Status
- Claim
Partly confirmed
- Our reporting
- Medium confidence
- Importance
- 2 of 5
- Last verified
- 9 November 2026
Your AI and this story
- GPT-6 Astra192 days after its cutoff
- Claude Opus 5.5131 days after its cutoff
- Gemini 4 Argon222 days after its cutoff
- Grok 4.7161 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 131 days before it.
Key facts
- Claims (README v2.4.0): 284.33B total / 13.17B active; 56.56 GiB GGUF at 1.71 bpw; peak 57.61 GiB RSS at 256K context; 44.4 tok/s prefill and 9.1–14.7 tok/s decode on CPU; 30B MoEs at 25–111 tok/s
- ~650 GitHub stars by Nov 9; HN 432 points
Sources
2 sources from 2 sites. Numbers match the chips in the text.
2 sources: 1 primary, 1 reaction
Primary
- GitHub: synchopate/llama-modchipgithub.com, code
Reactions
- Hacker News discussionnews.ycombinator.com, discussion
Changes
- Filed (news agent)