LLM EXPLORER 60,783 MODELS INDEXED

MiMo V2 Flash 4bit by mlx-community

By mlx-community · 643 downloads
HF Repo ↗ Copy URL

MiMo V2 Flash 4bit is an open-source language model by mlx-community. Features: 308.8b LLM, VRAM: 173.6GB, Context: 256K, License: mit, Quantized, LLM Explorer Score: 0.23.

  4-bit   4bit Base model:quantized:xiaomimim... Base model:xiaomimimo/mimo-v2-...   Conversational   Custom code   Mimo v2 flash   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiMo-V2-Flash-4bit 

MiMo V2 Flash 4bit Parameters and Internals

LLM NameMiMo V2 Flash 4bit
Repository 🤗https://huggingface.co/mlx-community/MiMo-V2-Flash-4bit 
Base Model(s)  MiMo V2 Flash   XiaomiMiMo/MiMo-V2-Flash
Model Size308.8b
Required VRAM173.6 GB
Updated2026-07-21
Maintainermlx-community
Model Typemimo_v2_flash
Model Files  5.3 GB: 1-of-36   5.0 GB: 2-of-36   4.9 GB: 3-of-36   4.9 GB: 4-of-36   4.9 GB: 5-of-36   4.9 GB: 6-of-36   4.9 GB: 7-of-36   4.9 GB: 8-of-36   4.9 GB: 9-of-36   4.9 GB: 10-of-36   4.9 GB: 11-of-36   4.9 GB: 12-of-36   4.9 GB: 13-of-36   4.9 GB: 14-of-36   4.9 GB: 15-of-36   4.9 GB: 16-of-36   4.9 GB: 17-of-36   4.9 GB: 18-of-36   4.9 GB: 19-of-36   4.9 GB: 20-of-36   4.9 GB: 21-of-36   4.9 GB: 22-of-36   4.9 GB: 23-of-36   4.9 GB: 24-of-36   4.9 GB: 25-of-36   4.9 GB: 26-of-36   4.9 GB: 27-of-36   4.9 GB: 28-of-36   4.9 GB: 29-of-36   4.9 GB: 30-of-36   4.9 GB: 31-of-36   4.9 GB: 32-of-36   4.9 GB: 33-of-36   4.9 GB: 34-of-36   4.9 GB: 35-of-36   1.6 GB: 36-of-36
Quantization Type4bit
Model ArchitectureMiMoV2FlashForCausalLM
Licensemit
Context Length262144
Model Max Length262144
Transformers Version4.40.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152576
Torch Data Typebfloat16
Errorsreplace