LLM EXPLORER 62,076 MODELS INDEXED

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

By mlx-community · 687 downloads
HF Repo ↗ Copy URL

MiMo V2.6 Flash RL Mxfp4 Q8 is an open-source language model by mlx-community. Features: 308.8b LLM, VRAM: 168.5GB, Context: 1024K, License: mit, Quantized, LLM Explorer Score: 0.33.

  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-Flash-RL-mxfp4-q8 

MiMo V2.6 Flash RL Mxfp4 Q8 Parameters and Internals

LLM NameMiMo V2.6 Flash RL Mxfp4 Q8
Repository 🤗https://huggingface.co/mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8 
Base Model(s)  XiaomiMiMo/MiMo-V2.6-Flash-RL   XiaomiMiMo/MiMo-V2.6-Flash-RL
Model Size308.8b
Required VRAM168.5 GB
Updated2026-09-24
Maintainermlx-community
Model Typemimo_v2
Model Files  4.6 GB: 1-of-36   4.7 GB: 2-of-36   4.7 GB: 3-of-36   4.8 GB: 4-of-36   4.7 GB: 5-of-36   4.7 GB: 6-of-36   4.8 GB: 7-of-36   4.7 GB: 8-of-36   4.7 GB: 9-of-36   4.8 GB: 10-of-36   4.7 GB: 11-of-36   4.7 GB: 12-of-36   4.8 GB: 13-of-36   4.7 GB: 14-of-36   4.7 GB: 15-of-36   4.8 GB: 16-of-36   4.7 GB: 17-of-36   4.7 GB: 18-of-36   4.8 GB: 19-of-36   4.7 GB: 20-of-36   4.7 GB: 21-of-36   4.8 GB: 22-of-36   4.7 GB: 23-of-36   4.7 GB: 24-of-36   4.8 GB: 25-of-36   4.7 GB: 26-of-36   4.7 GB: 27-of-36   4.8 GB: 28-of-36   4.7 GB: 29-of-36   4.7 GB: 30-of-36   4.8 GB: 31-of-36   4.7 GB: 32-of-36   4.7 GB: 33-of-36   4.8 GB: 34-of-36   4.7 GB: 35-of-36   3.0 GB: 36-of-36
Supported Languagesen zh
Quantization Typeq8
Model ArchitectureMiMoV2ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version5.3.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152576
Errorsreplace