Run 2.78T Params on 8GB RAM: Open-Source C99 Engine for Kimi K3
dr_cintas · x · 2026-08-07
A developer has released kimi-k3-in-c, a 176KB pure C99 inference engine that runs the 2.78 trillion parameter Kimi K3 model on just 8.24GB of RAM with a CPU.
It achieves this by streaming model experts from disk instead of loading them into memory. The project is 100% open-source and requires no GPU or CUDA.
Related event: Open-Source Pure C99 Engine Runs Trillion-Parameter Model on 8GB RAM(2 posts)→
More from Infra
- The Truth Behind MiniMax 2x Speedup: Newer Python Dependencies Introduced convrot Support — lmpdev · 2026-08-07
- Musk: Terafab AI Factory Phase 1 to Create Over 3,000 Jobs — elonmusk · 2026-08-07
- Meta Allegedly Building Own Search Engine, Scraping Web at Massive Scale — churchkey · 2026-08-07
- SanDisk Beats Earnings but Stock Falls as AI Inference Drives Memory Demand — ryanshrout · 2026-08-07
- Databricks CEO: Agent Traffic Will Be 1000x Human Traffic in 5 Years — threepointone · 2026-08-07
- Olares: Open-Source Personal Cloud OS for Self-Hosted AI Agents — tom_doerr · 2026-08-07