I'm uploading the Q8_0 first (normal quantization), then the usual Q5_K_M / Q4_K_M / IQ4_XS / IQ3_S MoE-quants afterwards.
Notes
04/28/26: While this model should run on the llama.cpp master branch, there was a small change to the inference code to support the
attention_value_scale
parameter. For the best accuacy/performance, I recommend pulling and compiling from this PR branch:
https://github.com/ggml-org/llama.cpp/pull/22493
.
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.
Quant
Size
Mixture
PPL
1-(Mean PPL(Q)/PPL(base))
KLD
Q8_0
305.68 GiB (8.50 BPW)
Q8_0
5.135221 ± 0.030263
+0.1229%
0.012455 ± 0.000173
Runs of AesSedai MiMo-V2.5-GGUF on huggingface.co
1.1K
Total runs
0
24-hour runs
-66
3-day runs
34
7-day runs
-249
30-day runs
More Information About MiMo-V2.5-GGUF huggingface.co Model
MiMo-V2.5-GGUF huggingface.co
MiMo-V2.5-GGUF huggingface.co is an AI model on huggingface.co that provides MiMo-V2.5-GGUF's model effect (), which can be used instantly with this AesSedai MiMo-V2.5-GGUF model. huggingface.co supports a free trial of the MiMo-V2.5-GGUF model, and also provides paid use of the MiMo-V2.5-GGUF. Support call MiMo-V2.5-GGUF model through api, including Node.js, Python, http.
MiMo-V2.5-GGUF huggingface.co is an online trial and call api platform, which integrates MiMo-V2.5-GGUF's modeling effects, including api services, and provides a free online trial of MiMo-V2.5-GGUF, you can try MiMo-V2.5-GGUF online for free by clicking the link below.
AesSedai MiMo-V2.5-GGUF online free url in huggingface.co:
MiMo-V2.5-GGUF is an open source model from GitHub that offers a free installation service, and any user can find MiMo-V2.5-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of MiMo-V2.5-GGUF install, users can directly use MiMo-V2.5-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.