What are the hardware requirements for Mistral Medium 3.5 128B BF16?

Mistral Medium 3.5 128B BF16 requires approximately 254.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Medium 3.5 128B BF16 and how large is it?

Mistral Medium 3.5 128B BF16 is developed by axolotl-ai-co, a model with 128b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Mistral Medium 3.5 128B BF16?

Mistral Medium 3.5 128B BF16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral Medium 3.5 128B BF16 by axolotl-ai-co — VRAM 254.9GB

Name: Mistral Medium 3.5 128B BF16
Author: axolotl-ai-co

Mistral Medium 3.5 128B BF16 is an open-source language model by axolotl-ai-co. Features: 128b LLM, VRAM: 254.9GB, License: other, LLM Explorer Score: 0.28.

Ar Bn De En Es Fa 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/axolotl-ai-co/Mistral-Medium-3.5-128B-BF16

Mistral Medium 3.5 128B BF16 Parameters and Internals

LLM Name	Mistral Medium 3.5 128B BF16
Repository 🤗	https://huggingface.co/axolotl-ai-co/Mistral-Medium-3.5-128B-BF16
Model Size	128b
Required VRAM	254.9 GB
Updated	2026-07-25
Maintainer	axolotl-ai-co
Model Type	mistral3
Model Files	8.6 GB: 1-of-29 8.6 GB: 2-of-29 9.0 GB: 3-of-29 9.0 GB: 4-of-29 9.0 GB: 5-of-29 8.6 GB: 6-of-29 8.6 GB: 7-of-29 9.0 GB: 8-of-29 9.0 GB: 9-of-29 9.0 GB: 10-of-29 8.6 GB: 11-of-29 8.6 GB: 12-of-29 9.0 GB: 13-of-29 9.0 GB: 14-of-29 9.0 GB: 15-of-29 8.6 GB: 16-of-29 8.6 GB: 17-of-29 9.0 GB: 18-of-29 9.0 GB: 19-of-29 9.0 GB: 20-of-29 8.6 GB: 21-of-29 8.6 GB: 22-of-29 9.0 GB: 23-of-29 9.0 GB: 24-of-29 9.0 GB: 25-of-29 8.6 GB: 26-of-29 8.6 GB: 27-of-29 11.4 GB: 28-of-29 5.3 GB: 29-of-29
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	Mistral3ForConditionalGeneration
License	other
Transformers Version	5.5.4
Tokenizer Class	TokenizersBackend
Padding Token	<pad>

Rank the Mistral Medium 3.5 128B BF16 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

Best Alternatives to Mistral Medium 3.5 128B BF16

Best Alternatives	Context / RAM	Downloads	Likes
Mistral Medium 3.5 128B GGUF	0K / 5.4 GB	20469	83
Tosilos 128B	0K / 255.4 GB	60	8

Note: green Score (e.g. "73.2") means that the model is better than axolotl-ai-co/Mistral-Medium-3.5-128B-BF16.