What are the hardware requirements for Magistral Small 2509?

Magistral Small 2509 requires approximately 48.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Magistral Small 2509 and how large is it?

Magistral Small 2509 is developed by unsloth, a model with 24b 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 Magistral Small 2509?

Magistral Small 2509 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Magistral Small 2509 by unsloth — VRAM 48.2GB, 128K context

Name: Magistral Small 2509
Author: unsloth

Magistral Small 2509 is an open-source language model by unsloth. Features: 24b LLM, VRAM: 48.2GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.2.

Arxiv:2506.10910 Ar Base model:finetune:mistralai/... Base model:mistralai/magistral... Bn De En Es Fa Fr Hi Id It Ja Ko Mistral-common 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/unsloth/Magistral-Small-2509

Magistral Small 2509 Parameters and Internals

LLM Name	Magistral Small 2509
Repository 🤗	https://huggingface.co/unsloth/Magistral-Small-2509
Base Model(s)	Magistral Small 2509 mistralai/Magistral-Small-2509
Model Size	24b
Required VRAM	48.2 GB
Updated	2026-07-18
Maintainer	unsloth
Model Files	4.9 GB: 1-of-10 4.8 GB: 2-of-10 4.9 GB: 3-of-10 4.8 GB: 4-of-10 4.8 GB: 5-of-10 4.9 GB: 6-of-10 4.8 GB: 7-of-10 4.8 GB: 8-of-10 4.9 GB: 9-of-10 4.6 GB: 10-of-10
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	apache-2.0
Context Length	131072
Model Max Length	131072
Tokenizer Class	LlamaTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072

Rank the Magistral Small 2509 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 Magistral Small 2509

Best Alternatives	Context / RAM	Downloads	Likes
...tral Small 2 24B Instruct 2512	384K / 51.6 GB	240440	618
...Small 2 24B Instruct 2512 Bf16	384K / 47.8 GB	367	4
...al Small 3.2 24B Instruct 2506	128K / 48.2 GB	312176	602
Devstral Small 2507	128K / 47.3 GB	116445	368
Magistral Small 2509	128K / 48.2 GB	33508	305
Devstral Small 2505	128K / 47.3 GB	4960	867
...4B Magistral PaperWitch Heresy	128K / 48.2 GB	38	1
...istral Small 3.1 24B Base 2503	128K / 48.2 GB	1363	272
Magistral 2509 24B Text Only	128K / 47.3 GB	47	16
...mall 3.2 24B Instruct 2506 FP8	128K / 25.8 GB	81	6

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Magistral-Small-2509.