What are the hardware requirements for Mistral Small 3.2 24B Instruct 2506 8bit?

Mistral Small 3.2 24B Instruct 2506 8bit requires approximately 25 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Small 3.2 24B Instruct 2506 8bit and how large is it?

Mistral Small 3.2 24B Instruct 2506 8bit is developed by mlx-community, a model with 24b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Mistral Small 3.2 24B Instruct 2506 8bit perform on standard benchmarks?

Mistral Small 3.2 24B Instruct 2506 8bit has the following published scores: LMSYS ELO 1335. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral Small 3.2 24B Instruct 2506 8bit by mlx-community — VRAM 25GB

Name: Mistral Small 3.2 24B Instruct 2506 8bit
Author: mlx-community

Mistral Small 3.2 24B Instruct 2506 8bit is an open-source language model by mlx-community. Features: 24b LLM, VRAM: 25GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.32, ELO: 1335.

8-bit 8bit Ar Base model:mistralai/mistral-s... Base model:quantized:mistralai... Bn De En Es Fa Fr Hi Id Instruct It Ja Ko Mistral3 Mlx Ms Ne Pl Pt Quantized Region:us Ro Ru Safetensors Sharded Sr Sv Tensorflow Tr Uk Vi Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit

Mistral Small 3.2 24B Instruct 2506 8bit Benchmarks

LMSys ELO 1335 vs 1272 (so35) 5%

^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 Small 3.2 24B Instruct 2506 8bit Parameters and Internals

LLM Name	Mistral Small 3.2 24B Instruct 2506 8bit
Repository 🤗	https://huggingface.co/mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
Base Model(s)	mistralai/Mistral-Small-3.2-24B-Instruct-2506 mistralai/Mistral-Small-3.2-24B-Instruct-2506
Model Size	24b
Required VRAM	25 GB
Updated	2026-08-05
Maintainer	mlx-community
Model Type	mistral3
Instruction-Based	Yes
Model Files	5.3 GB: 1-of-5 5.3 GB: 2-of-5 5.3 GB: 3-of-5 5.3 GB: 4-of-5 3.8 GB: 5-of-5
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
Quantization Type	8bit
Model Architecture	Mistral3ForConditionalGeneration
License	apache-2.0
Transformers Version	4.52.4
Tokenizer Class	LlamaTokenizerFast
Torch Data Type	bfloat16

Rank the Mistral Small 3.2 24B Instruct 2506 8bit 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 Small 3.2 24B Instruct 2506 8bit

Best Alternatives	Context / RAM	Downloads	Likes
...3.2 24B Instruct 2506 Bnb 4bit	0K / 14.5 GB	7430	10
...Instruct 2506 Unsloth Bnb 4bit	0K / 14.6 GB	2107	13
...2 24B Instruct 2512 OptiQ 4bit	0K / 16.5 GB	422	1
...l 2 24B Instruct 2512 MLX 8Bit	0K / 25 GB	3915	6
...all 3.2 24B Instruct 2506 4bit	0K / 13.3 GB	682	1
...resolvable Pattern Finetune V1	0K / 48.2 GB	55	0
... 2 24B Instruct 2512 MLX MXFP4	0K / 12.5 GB	1377	4
Devstral Small 2507 GGUF	0K / 0.9 GB	4818	80
...all 3.2 24B Instruct 2506 Bf16	0K / 46.9 GB	128	1

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit.