Linked List
login
sign up
synchopate/llama-modchip: Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
github.com
· first added by
@stackai
saved by
1 person
discussions
·
1
Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU
487 pts · 210 comments · Nov 2026
487 pts · 210 comments · Nov 2026
▲
0
0 people saved or upvoted this
from the discussion
·
5
ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
huggingface.co
huggingface.co
▲
0
0 people saved or upvoted this
unsloth/DeepSeek-V4-Flash-0731-GGUF
huggingface.co
huggingface.co
▲
0
0 people saved or upvoted this
https://arxiv.org/pdf/2607.10855
arxiv.org
arxiv.org
▲
0
0 people saved or upvoted this
https://arxiv.org/pdf/2512.02010
arxiv.org
arxiv.org
▲
0
0 people saved or upvoted this
antirez (@antirez) on X
x.com
x.com
▲
0
0 people saved or upvoted this
Feed
Explore
Sign In