LLM EXPLORER 62,589 MODELS INDEXED

MiMo V2.6 Pro RL Mxfp4 Q8 by mlx-community

By mlx-community · 772 downloads
HF Repo ↗ Copy URL

MiMo V2.6 Pro RL Mxfp4 Q8 is an open-source language model by mlx-community. Features: 1021.2b LLM, VRAM: 212.3GB, Context: 1024K, License: mit, Quantized, LLM Explorer Score: 0.32.

  4-bit   Agent Base model:quantized:xiaomimim... Base model:xiaomimimo/mimo-v2....   Conversational   Custom code   En   Long-context   Mimo v2   Mlx   Q8   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiMo-V2.6-Pro-RL-mxfp4-q8 

MiMo V2.6 Pro RL Mxfp4 Q8 Parameters and Internals

LLM NameMiMo V2.6 Pro RL Mxfp4 Q8
Repository 🤗https://huggingface.co/mlx-community/MiMo-V2.6-Pro-RL-mxfp4-q8 
Base Model(s)  XiaomiMiMo/MiMo-V2.6-Pro-RL   XiaomiMiMo/MiMo-V2.6-Pro-RL
Model Size1021.2b
Required VRAM212.3 GB
Updated2026-09-30
Maintainermlx-community
Model Typemimo_v2
Model Files  4.5 GB: 1-of-116   5.3 GB: 2-of-116   5.2 GB: 3-of-116   5.3 GB: 4-of-116   5.3 GB: 5-of-116   5.3 GB: 6-of-116   3.0 GB: 7-of-116   5.1 GB: 8-of-116   5.3 GB: 9-of-116   5.3 GB: 10-of-116   5.3 GB: 11-of-116   3.0 GB: 12-of-116   5.1 GB: 13-of-116   5.3 GB: 14-of-116   5.3 GB: 15-of-116   5.3 GB: 16-of-116   3.0 GB: 17-of-116   5.1 GB: 18-of-116   5.3 GB: 19-of-116   5.3 GB: 20-of-116   5.3 GB: 21-of-116   3.0 GB: 22-of-116   5.1 GB: 23-of-116   5.3 GB: 24-of-116   5.3 GB: 25-of-116   5.3 GB: 26-of-116   3.0 GB: 27-of-116   5.1 GB: 28-of-116   5.3 GB: 29-of-116   5.3 GB: 30-of-116   5.3 GB: 31-of-116   3.0 GB: 32-of-116   5.1 GB: 33-of-116   5.3 GB: 34-of-116   5.3 GB: 35-of-116   5.3 GB: 36-of-116   3.0 GB: 37-of-116   5.1 GB: 38-of-116   5.3 GB: 39-of-116   5.3 GB: 40-of-116   5.3 GB: 41-of-116   3.0 GB: 42-of-116   5.1 GB: 43-of-116   5.3 GB: 44-of-116
Supported Languagesen zh
Quantization Typeq8
Model ArchitectureMiMoV2ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version5.3.0
Vocabulary Size152576