cd/entity/deepseek-v4-in-cยท homeโ€บ entitiesโ€บ deepseek-v4-in-c
grep -l @deepseek-v4-in-c /news/*.json | wc -l โ†’ 1

deepseek-v4-in-c

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

13:54
2026-08-21
dev.to
large-language-models

I Ran a 284B-Parameter LLM From 3.2GB of RAM โ€” in Plain C

A developer built a C99 inference engine that runs DeepSeek-V4-Flash, a 284B-parameter mixture-of-experts model, on a laptop with just 3.2GB of RAM by streaming weights off NVMe and caching only the eโ€ฆ

// co-occurs with top 7 entities
// topics top 3 topics