Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU
62 comments
- Points6
- Comments3
62 comments
Story details from Hacker News ↗ · linked article on github.com.
Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU was first seen on Hacker News · Front page on Nov 8, 2026. Since then it has appeared in 24 checks on 1 different day. Its best position was #8 of 30, reached on Nov 8, 17:24 UTC. It is #8 right now, climbing from #10 to #8 over the last 6 checks.
Position on Hacker News · Front page at every check (lower is better).
Best rank per day (UTC).
points as reported by Hacker News.
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
At which quantization? That's the only thing I want to know. EDIT: I think it's 2 bit? If so, would be curious to see the quality of the output. Not great, I think.
This is quite an obnoxious Readme.md with AI slop. It wraps around llama.cpp but without seeing what platform assumptions it makes its unclear for other readers whether this is worth testing.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 17:39 UTC it is #8, climbing from #10 to #8 over the last 6 checks.
#8 on Hacker News · Front page, on Nov 8, 17:24 UTC. Trendoday checks this list every 15 minutes.
It was first seen on Nov 8, 2026 and has been on the list on 1 day (24 checks) since.
6 points and 3 comments; submitted by joshcsimmons on Nov 8, 2026.