LLM EXPLORER 59,516 MODELS INDEXED

Mistral Medium 3.5 128B NVFP4 by nvidia

By nvidia · 30029 downloads
HF Repo ↗ Copy URL

Mistral Medium 3.5 128B NVFP4 is an open-source language model by nvidia. Features: 128b LLM, VRAM: 95.2GB, Context: 256K, License: other, LLM Explorer Score: 0.34.

  8-bit Base model:mistralai/mistral-m... Base model:quantized:mistralai...   Conversational   Mistral   Mistral-medium-3.5   Mistral3   Model optimizer   Modelopt   Nvfp4   Nvidia   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Mistral-Medium-3.5-128B-NVFP4 

Mistral Medium 3.5 128B NVFP4 Parameters and Internals

LLM NameMistral Medium 3.5 128B NVFP4
Repository 🤗https://huggingface.co/nvidia/Mistral-Medium-3.5-128B-NVFP4 
Base Model(s)  mistralai/Mistral-Medium-3.5-128B   mistralai/Mistral-Medium-3.5-128B
Model Size128b
Required VRAM95.2 GB
Updated2026-07-30
Maintainernvidia
Model Files  10.0 GB: 1-of-10   9.9 GB: 2-of-10   10.0 GB: 3-of-10   9.9 GB: 4-of-10   9.9 GB: 5-of-10   9.9 GB: 6-of-10   10.0 GB: 7-of-10   10.0 GB: 8-of-10   9.9 GB: 9-of-10   5.7 GB: 10-of-10
Model ArchitectureMambaSSM
Licenseother
Context Length262144
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<pad>
Vocabulary Size131072

Best Alternatives to Mistral Medium 3.5 128B NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
Mistral Medium 3.5 128B256K / 267.2 GB107147417
Mistral Medium 3.5 128B 4bit256K / 77.7 GB14574
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Mistral-Medium-3.5-128B-NVFP4.