AirLLM 2.8T LLM inference with single 4GB GPU
- chinese-nlp
- finetune
- generative-ai
- instruct-gpt
Repository Index
68,261 visible repositories in the index
1–2 of 2 · Most stars
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).