Topic
CPU Inference
DeepSeek V4-Flash on a 64GB CPU box: a claim, not a result
llama-modchip claims a 284B DeepSeek V4-Flash quant runs CPU-only in 57.6GB RAM at 9-14 tok/s. All figures are author-reported and unreproduced.

Topic
llama-modchip claims a 284B DeepSeek V4-Flash quant runs CPU-only in 57.6GB RAM at 9-14 tok/s. All figures are author-reported and unreproduced.

Sponsor disclosure — not editorial
Powered by Morpheus and StrandCMS. Morpheus is a decentralized inference marketplace, covered on the same terms as every other provider. StrandCMS is the open-source, agent-first framework this site is built on.
Learn more →