What are the hardware requirements for Devstral Small 2507 4bit DWQ?

Devstral Small 2507 4bit DWQ requires approximately 13.3 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 Small 2507 4bit DWQ and how large is it?

Devstral Small 2507 4bit DWQ 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 Small 2507 4bit DWQ?

Devstral Small 2507 4bit DWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Devstral Small 2507 4bit DWQ by mlx-community — VRAM 13.3GB, 128K context

Name: Devstral Small 2507 4bit DWQ
Author: mlx-community

Devstral Small 2507 4bit DWQ is an open-source language model by mlx-community. Features: 23.6b LLM, VRAM: 13.3GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.

4-bit 4bit Ar Base model:mlx-community/devst... Base model:quantized:mlx-commu... Bn Conversational De En Es Fa Fr Hi Id It Ja Ko Mistral 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/Devstral-Small-2507-4bit-DWQ

Devstral Small 2507 4bit DWQ Parameters and Internals

LLM Name	Devstral Small 2507 4bit DWQ
Repository 🤗	https://huggingface.co/mlx-community/Devstral-Small-2507-4bit-DWQ
Base Model(s)	Devstral Samll 2507 Bf16 mlx-community/Devstral-Samll-2507-bf16
Model Size	23.6b
Required VRAM	13.3 GB
Updated	2026-07-15
Maintainer	mlx-community
Model Type	mistral
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 pt it ja ko ru zh ar fa id ms ne pl ro sr sv tr uk vi hi bn
Quantization Type	4bit
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 Small 2507 4bit DWQ 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 Devstral Small 2507 4bit DWQ

Best Alternatives	Context / RAM	Downloads	Likes
...onCriminalComputingConfig 4bit	32K / 13.3 GB	28	1
...onCriminalComputingConfig 6bit	32K / 19.2 GB	24	1
Magistral Small 2506 4bit DWQ	32K / 13.3 GB	31	3
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 Samll 2507 Bf16	128K / 46.9 GB	24	1
Devstral Small 2505 Bf16	128K / 46.9 GB	55	1
Magistral Small 2506	40K / 47.3 GB	36	0

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Devstral-Small-2507-4bit-DWQ.