What are the hardware requirements for Devstral Samll 2507 Bf16?

Devstral Samll 2507 Bf16 requires approximately 46.9 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 Devstral Samll 2507 Bf16 and how large is it?

Devstral Samll 2507 Bf16 is developed by mlx-community, a model with 23.6b 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 Devstral Samll 2507 Bf16?

Devstral Samll 2507 Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Devstral Samll 2507 Bf16 by mlx-community — VRAM 46.9GB, 128K context

Name: Devstral Samll 2507 Bf16
Author: mlx-community

Devstral Samll 2507 Bf16 is an open-source language model by mlx-community. Features: 23.6b LLM, VRAM: 46.9GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.19.

Ar Base model:finetune:mistralai/... Base model:mistralai/devstral-... Bn Conversational De En Es Fa Fr Hi Id It Ja Ko Mistral Mlx Ms Ne Pl Pt Region:us Ro Ru Safetensors Sharded Sr Sv Tensorflow Tr Uk Vi Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/Devstral-Samll-2507-bf16

Devstral Samll 2507 Bf16 Parameters and Internals

LLM Name	Devstral Samll 2507 Bf16
Repository 🤗	https://huggingface.co/mlx-community/Devstral-Samll-2507-bf16
Base Model(s)	Devstral Small 2507 mistralai/Devstral-Small-2507
Model Size	23.6b
Required VRAM	46.9 GB
Updated	2026-07-26
Maintainer	mlx-community
Model Type	mistral
Model Files	5.1 GB: 1-of-10 5.2 GB: 2-of-10 5.1 GB: 3-of-10 5.2 GB: 4-of-10 5.2 GB: 5-of-10 5.1 GB: 6-of-10 5.2 GB: 7-of-10 5.2 GB: 8-of-10 4.3 GB: 9-of-10 1.3 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	MistralForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.53.1
Tokenizer Class	LlamaTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Devstral Samll 2507 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 Devstral Samll 2507 Bf16

Model	Likes	Downloads	VRAM
Devstral Small 2507 4bit DWQ	12	166	13 GB

Best Alternatives to Devstral Samll 2507 Bf16

Best Alternatives	Context / RAM	Downloads	Likes
MagiSeek V1.1	128K / 47.3 GB	77	1
Experiment024b	128K / 47.3 GB	14	3
Chat KTO	128K / 47.3 GB	7	0
Chat KTO	128K / 47.3 GB	6	0
Devstral Small 2505 Bf16	128K / 46.9 GB	55	1
Magistral Small 2506	40K / 47.3 GB	36	0
...stral Small 2501 Tensopolis V1	32K / 47.3 GB	6	0
XortronCriminalComputingConfig	32K / 47.3 GB	314	172
Magistral Small 2506 Bf16	32K / 46.9 GB	33	10
Sandmisthink24BKaalpac	32K / 47.3 GB	32	0

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Devstral-Samll-2507-bf16.