Notes

• 05/08/26: The CUDA flash attention branch has also been merged to master, please use the master branch and recompile!
• 05/07/26: The PR branch has been merged to master. All of the quants and imatrix have been updated with the newest conversion and are ready to re-download. These quants include MTP tensors for when that gets added upstream eventually.
• 05/05/26:
• 05/03/26: WIP vision support on this branch: https://github.com/AesSedai/llama.cpp/tree/mimo-v2.5-vision (if it's broken with F16 mmproj, pull the latest commit and recompile, or try the BF16 mmproj) and uploaded mmproj files
• 05/01/26:
• 04/28/26:

Model

This is a text-only GGUF quantization of XiaomiMiMo/MiMo-V2.5. This means that image and audio input is not present in this GGUF, and will not be available until support is added upstream in llama.cpp.

This repo contains specialized MoE-quants for MiMo-V2.5. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.

👁 Chart showing Pareto KLD analysis of quants
👁 Chart showing Pareto PPL analysis of quants

Base model