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: 0.41.
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 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Mistral Medium 3.5 128B NVFP4 Parameters and Internals
| LLM Name | Mistral Medium 3.5 128B NVFP4 |
| Repository 🤗 | https://huggingface.co/nvidia/Mistral-Medium-3.5-128B-NVFP4 |
| Base Model(s) | |
| Model Size | 128b |
| Required VRAM | 95.2 GB |
| Updated | 2026-07-05 |
| Maintainer | nvidia |
| Model Files | |
| Model Architecture | MambaSSM |
| License | other |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
Best Alternatives to Mistral Medium 3.5 128B NVFP4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral Medium 3.5 128B | 256K / 267.2 GB | 320057 | 386 |
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Mistral-Medium-3.5-128B-NVFP4 .
Rank the Mistral Medium 3.5 128B NVFP4 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 54807 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a