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 eโฆ