DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks
Repository Index
98,836 visible repositories in the index
1–3 of 3 · 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).
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
- llm
- vlm
- finetuning
- gemma3