What are the hardware requirements for Mistral Small 24B Instruct 2501 4bit?

Mistral Small 24B Instruct 2501 4bit requires approximately 13.3 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Small 24B Instruct 2501 4bit and how large is it?

Mistral Small 24B Instruct 2501 4bit 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 24B Instruct 2501 4bit perform on standard benchmarks?

Mistral Small 24B Instruct 2501 4bit has the following published scores: LMSYS ELO 1233. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral Small 24B Instruct 2501 4bit by mlx-community — VRAM 13.3GB, 32K context

Name: Mistral Small 24B Instruct 2501 4bit
Author: mlx-community

Mistral Small 24B Instruct 2501 4bit is an open-source language model by mlx-community. Features: 24b LLM, VRAM: 13.3GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.3, ELO: 1233.

4-bit 4bit Base model:mistralai/mistral-s... Base model:quantized:mistralai... De En Es Fr Instruct It Ja Ko Mistral Mlx Pt Quantized Region:us Ru Safetensors Sharded Tensorflow Vllm Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/Mistral-Small-24B-Instruct-2501-4bit

Mistral Small 24B Instruct 2501 4bit Benchmarks

LMSys ELO 1233 vs 1272 (so35) -3.1%

^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 24B Instruct 2501 4bit Parameters and Internals

LLM Name	Mistral Small 24B Instruct 2501 4bit
Repository 🤗	https://huggingface.co/mlx-community/Mistral-Small-24B-Instruct-2501-4bit
Base Model(s)	...istral Small 24B Instruct 2501 mistralai/Mistral-Small-24B-Instruct-2501
Model Size	24b
Required VRAM	13.3 GB
Updated	2026-07-30
Maintainer	mlx-community
Model Type	mistral
Instruction-Based	Yes
Model Files	5.3 GB: 1-of-3 5.3 GB: 2-of-3 2.7 GB: 3-of-3
Supported Languages	en fr de es it pt zh ja ru ko
Quantization Type	4bit
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.49.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Mistral Small 24B Instruct 2501 4bit 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 24B Instruct 2501 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Devstral Small 2507 Bnb 4bit	128K / 14.2 GB	398	1
...al Small 2507 Unsloth Bnb 4bit	128K / 15 GB	128	5
...al Small 2506 Unsloth Bnb 4bit	40K / 15 GB	109	4
Magistral Small 2506 Bnb 4bit	40K / 14.2 GB	38	1
Not So Small Alpaca 24B	32K / 47.3 GB	14	0
Napoleon 24B V0.0	32K / 47.3 GB	18	0
...all 24B Instruct 2501 Bnb 4bit	32K / 14.2 GB	4725	3
...Instruct 2501 Unsloth Bnb 4bit	32K / 15 GB	2955	19
...b With Nemotron Converted Vllm	32K / 47.3 GB	38	0
...24B Base 2501 Unsloth Bnb 4bit	32K / 15.7 GB	116	3