What are the hardware requirements for Mistral Medium 3.5 128B?

Mistral Medium 3.5 128B requires approximately 267.2 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Medium 3.5 128B and how large is it?

Mistral Medium 3.5 128B is developed by mistralai, a model with 128b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Mistral Medium 3.5 128B perform on standard benchmarks?

Mistral Medium 3.5 128B has the following published scores: LMSYS ELO 1387. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral Medium 3.5 128B by mistralai — VRAM 267.2GB, 256K context

Name: Mistral Medium 3.5 128B
Author: mistralai

Mistral Medium 3.5 128B is an open-source language model by mistralai. Features: 128b LLM, VRAM: 267.2GB, Context: 256K, License: MNPL-0.1, LLM Explorer Score: 0.51, ELO: 1387.

Ar Bn De En Es Eval-results Fa Fp8 Fr Hi Id It Ja Ko Mistral3 Ms Ne Pl Pt Region:us Ro Ru Safetensors Sharded Sr Sv Tensorflow Tr Uk Vi Vllm Zh

Model Card on HF 🤗: https://huggingface.co/mistralai/Mistral-Medium-3.5-128B

Mistral Medium 3.5 128B Benchmarks

LMSys ELO 1387 vs 1272 (so35) 9%

^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 Parameters and Internals

LLM Name	Mistral Medium 3.5 128B
Repository 🤗	https://huggingface.co/mistralai/Mistral-Medium-3.5-128B
Model Size	128b
Required VRAM	267.2 GB
Updated	2026-08-06
Maintainer	mistralai
Model Files	50.0 GB: 1-of-3 50.0 GB: 2-of-3 33.6 GB: 3-of-3 49.8 GB: 1-of-3 49.8 GB: 2-of-3 34.0 GB: 3-of-3
Supported Languages	en fr de es pt it ja ko ru zh ar fa id ms ne pl ro sr sv tr uk vi hi bn
Model Architecture	MambaSSM
License	MNPL-0.1
Context Length	262144
Model Max Length	262144
Tokenizer Class	TokenizersBackend
Padding Token	<pad>
Vocabulary Size	131072

Rank the Mistral Medium 3.5 128B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Mistral Medium 3.5 128B

Model	Likes	Downloads	VRAM
Mistral Medium 3.5 128B GGUF	83	20469	5 GB
Tosilos 128B	8	60	255 GB

Best Alternatives to Mistral Medium 3.5 128B

Best Alternatives	Context / RAM	Downloads	Likes
Mistral Medium 3.5 128B NVFP4	256K / 95.2 GB	30029	29
Mistral Medium 3.5 128B 4bit	256K / 77.7 GB	1457	4