LLM EXPLORER 59,516 MODELS INDEXED

Mistral Medium 3.5 128B 4bit by mlx-community

By mlx-community · 1457 downloads
HF Repo ↗ Copy URL

Mistral Medium 3.5 128B 4bit is an open-source language model by mlx-community. Features: 128b LLM, VRAM: 77.7GB, Context: 256K, Quantized, LLM Explorer Score: 0.27.

  4-bit   4bit   Conversational   En   Image-text-to-text   Mistral3   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Mistral-Medium-3.5-128B-4bit 

Mistral Medium 3.5 128B 4bit Parameters and Internals

LLM NameMistral Medium 3.5 128B 4bit
Repository 🤗https://huggingface.co/mlx-community/Mistral-Medium-3.5-128B-4bit 
Model Size128b
Required VRAM77.7 GB
Updated2026-08-10
Maintainermlx-community
Model Files  5.4 GB: 1-of-15   5.4 GB: 2-of-15   5.3 GB: 3-of-15   5.2 GB: 4-of-15   5.4 GB: 5-of-15   5.3 GB: 6-of-15   5.2 GB: 7-of-15   5.2 GB: 8-of-15   5.2 GB: 9-of-15   5.4 GB: 10-of-15   5.3 GB: 11-of-15   5.2 GB: 12-of-15   5.2 GB: 13-of-15   5.2 GB: 14-of-15   3.8 GB: 15-of-15
Supported Languagesen
Quantization Type4bit
Model ArchitectureMambaSSM
Context Length262144
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<pad>
Vocabulary Size131072

Best Alternatives to Mistral Medium 3.5 128B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Mistral Medium 3.5 128B256K / 267.2 GB107147417
Mistral Medium 3.5 128B NVFP4256K / 95.2 GB3002929
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mistral-Medium-3.5-128B-4bit.