lyogavin/airllm

AirLLM 2.8T LLM inference with single 4GB GPU

232 best points · 84 comments · 3 Hacker News posts · 41,884 GitHub stars · View on GitHub

Hacker News discussions

• AirLLM 70B inference with single 4GB GPU (232 points, 84 comments, by Anon84, 2026-08-03)
• AirLLM optimizes inference memory usage (2 points, 0 comments, by nreece, 2026-03-08)
• AirLLM: Inference 2.8T Kimi K3 on a single 4GB GPU (2 points, 0 comments, by maxloh, 2026-08-02)