IQ3_XXS (~3.2 BPW). For me this is an option because my Mac studio is only used for serving LLMs, so I can afford to dedicate most of its RAM to this. I can run with 256k context and only uses ~117G, with the remaining (up to 125G which I can allocate to VRAM) being used for prompt caching and context checkpoints.
I'm making my own quants, though the Vision-Exp version is outdated and won't work on llama.cpp master branch (I built it before llama added support):
alt Hacker News
IQ3_XXS (~3.2 BPW). For me this is an option because my Mac studio is only used for serving LLMs, so I can afford to dedicate most of its RAM to this. I can run with 256k context and only uses ~117G, with the remaining (up to 125G which I can allocate to VRAM) being used for prompt caching and context checkpoints.
I'm making my own quants, though the Vision-Exp version is outdated and won't work on llama.cpp master branch (I built it before llama added support):
- https://huggingface.co/tarruda/DeepSeek-V4-Flash-0731-GGUF
- https://huggingface.co/tarruda/DeepSeek-V4-Flash-Vision-Exp-...
For the Vision-exp version, I also ran perplexity + KLD against the original MXFP4. Seems quite OK: https://huggingface.co/tarruda/DeepSeek-V4-Flash-Vision-Exp-...