What are the hardware requirements for Mistral Small 4 119B 2603 Bf16?

Mistral Small 4 119B 2603 Bf16 requires approximately 191.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Small 4 119B 2603 Bf16 and how large is it?

Mistral Small 4 119B 2603 Bf16 is developed by mlx-community, a model with 119b 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 Small 4 119B 2603 Bf16?

Mistral Small 4 119B 2603 Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral Small 4 119B 2603 Bf16 by mlx-community — VRAM 191.9GB

Name: Mistral Small 4 119B 2603 Bf16
Author: mlx-community

Mistral Small 4 119B 2603 Bf16 is an open-source language model by mlx-community. Features: 119b LLM, VRAM: 191.9GB, License: apache-2.0, LLM Explorer Score: 0.23.

Ar Bn De En Es Fa Fp8 Fr Hi Id It Ja Ko Mistral3 Mlx 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/mlx-community/Mistral-Small-4-119B-2603-bf16

Mistral Small 4 119B 2603 Bf16 Parameters and Internals

LLM Name	Mistral Small 4 119B 2603 Bf16
Repository 🤗	https://huggingface.co/mlx-community/Mistral-Small-4-119B-2603-bf16
Model Size	119b
Required VRAM	191.9 GB
Updated	2026-08-06
Maintainer	mlx-community
Model Type	mistral3
Model Files	4.1 GB: 1-of-55 4.4 GB: 2-of-55 4.3 GB: 3-of-55 4.4 GB: 4-of-55 4.4 GB: 5-of-55 4.3 GB: 6-of-55 4.4 GB: 7-of-55 4.4 GB: 8-of-55 4.3 GB: 9-of-55 4.4 GB: 10-of-55 4.4 GB: 11-of-55 4.3 GB: 12-of-55 4.4 GB: 13-of-55 4.4 GB: 14-of-55 4.3 GB: 15-of-55 4.4 GB: 16-of-55 4.4 GB: 17-of-55 4.3 GB: 18-of-55 4.4 GB: 19-of-55 4.4 GB: 20-of-55 4.3 GB: 21-of-55 4.4 GB: 22-of-55 4.4 GB: 23-of-55 4.3 GB: 24-of-55 4.4 GB: 25-of-55 4.4 GB: 26-of-55 4.3 GB: 27-of-55 4.4 GB: 28-of-55 4.4 GB: 29-of-55 4.3 GB: 30-of-55 4.4 GB: 31-of-55 4.4 GB: 32-of-55 4.3 GB: 33-of-55 4.4 GB: 34-of-55 4.4 GB: 35-of-55 4.3 GB: 36-of-55 4.4 GB: 37-of-55 4.4 GB: 38-of-55 4.3 GB: 39-of-55 4.4 GB: 40-of-55 4.4 GB: 41-of-55 4.3 GB: 42-of-55 4.4 GB: 43-of-55 4.4 GB: 44-of-55
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	apache-2.0
Transformers Version	5.3.0.dev0

Rank the Mistral Small 4 119B 2603 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

Quantized Models of the Mistral Small 4 119B 2603 Bf16

Model	Likes	Downloads	VRAM
...l Small 4 119B 2603 OptiQ 2bit	2	938	45 GB

Best Alternatives to Mistral Small 4 119B 2603 Bf16

Best Alternatives	Context / RAM	Downloads	Likes
...l Small 4 119B 2603 OptiQ 2bit	0K / 45 GB	938	2

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mistral-Small-4-119B-2603-bf16.