From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.mistralSubject: Devstral-Small-2505-4bit Date: 2026-11-15Commit: 91ab747Signed: 2DC28CC7B26A283B ✓ Text generation model with 23.6B parameters. Safetensors weights, 13.3 GB in all. Published by mlx-community under Apache-2.0.
23.6B params 13.3 GB Devstral-Small-2505-4bit safetensors permissive Facts Params 23.6B Size 13.3 GB Formats safetensors Task text generation License Apache-2.0 permissive
fw
$ fw get mlx-community/Devstral-Small-2505-4bit
# manifest sha256 fa06132bd290… · 13.3 GB · 12 files
$ fw verify ./Devstral-Small-2505-4bit mlx-community/Devstral-Small-2505-4bitHosted (signed) mlx-community/Devstral-Small-2505-4bit Last check: 2026-11-15 05:19 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of Devstral-Small-2505 .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 13.3 GB
Weights 13.3 GB (safetensors)
Parameters 23.6B
Formats safetensors
Task text generation
License Apache-2.0 (permissive)
Files 12, each with a sha256
Publisher mlx-community
Added 2026-11-15
Section alt.freeweights.mistral Lineage
Original release from the publisher.
Base model: mistralai/Devstral-Small-2505
Where these bytes come from
Publisher at the pinned commit →You
Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge Host Last check Result huggingface.co 2026-11-15 05:19 UTC passed
Model card From the publisher at commit
91ab747 . Shown as plain text with links; images open at the publisher.
This model mlx-community/Devstral-Small-2505-4bit was converted to MLX format from mistralai/Devstral-Small-2505 using mlx-lm version 0.24.1 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Devstral-Small-2505-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True) Files 12 files · 13.3 GB Weights 13.3 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256 File Size sha256 .gitattributes 1.57 KB 34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930 README.md 1.19 KB 7c51fc03019ba8c1a4770ecc383a7d942b324d680adc755c5560065392070aac chat_template.json 2.77 KB 05bf76e1e583e0b8b337bbc469bb4bf0914a38313589f7864a2941829739df37 config.json 822 B 8b1e22be32a8e06b513a81c460be0b6c671ea7b756d447e66131dedadac049a5 generation_config.json 111 B 46a6e46680317fe06de9a5e1b2bcc4cf2965245b4994dab4600ba4be4860f1b8 model-00001-of-00003.safetensors 5.29 GB 864b18f71ddbd0d28680decd05eb1d894c3177f3819b849dfa58f21737a71ce5 model-00002-of-00003.safetensors 5.31 GB 803e8e23b06b44863c57a10b9c5f7bb4ecb3ec4ecb240c6c7e182f50a68c4335 model-00003-of-00003.safetensors 2.66 GB 7ad224210e20fcf57defd6d2073dab23aa7a0a3c50b6ba572e8ad39ff6a915ac model.safetensors.index.json 79.3 KB 42180bd2e96e647bf8528c861f5c25adfbf8dfa87e12fe6e7662df4beeafe5f0 special_tokens_map.json 21.3 KB 5bc5d1c106bf86895473568ef5211f3fde8415e6fdee039223d6db8ca52cbe01 tokenizer.json 17.1 MB b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949 tokenizer_config.json 200 KB 9071c2c00bc472e77d1b257078fde3b56146663296cf106ac257c3e5fa66a567
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 91ab747273 pinned now 2026-11-15 05:19 UTC 12 files · 13.3 GB
Use it fw
$ fw get mlx-community/Devstral-Small-2505-4bit
# manifest sha256 fa06132bd290… · 13.3 GB · 12 files
$ fw verify ./Devstral-Small-2505-4bit mlx-community/Devstral-Small-2505-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Devstral-Small-2505-4bit.json --dir ./Devstral-Small-2505-4bit
$ python3 fw.py verify ./Devstral-Small-2505-4bit ./mlx-community__Devstral-Small-2505-4bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/Devstral-Small-2505-4bit --revision 91ab74727385430dac575c8b0a27235367870cb6 --local-dir ./Devstral-Small-2505-4bittransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("mlx-community/Devstral-Small-2505-4bit", revision="91ab74727385430dac575c8b0a27235367870cb6")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Devstral-Small-2505-4bit", revision="91ab74727385430dac575c8b0a27235367870cb6", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/Devstral-Small-2505-4bit --revision 91ab74727385430dac575c8b0a27235367870cb6License Name Apache License 2.0 Id Apache-2.0 Class Permissive Redistribution yes Listing Hosted (signed) Decided License as declared by the publisher. No person read it. 2026-11-15 Text in README.md Text sha256 7c51fc03019ba8c1a4770ecc383a7d942b324d680adc755c5560065392070aac Terms gate No extra terms beyond the license. Read the license text
Licenses are checked against the license table . A custom license passes only after a person reads it.
Provenance From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.mistralSubject: Devstral-Small-2505-4bit Date: 2026-11-15Commit: 91ab747Signed: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Devstral-Small-2505-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Devstral-Small-2505-4bit.json.minisig
$ minisign -Vm Devstral-Small-2505-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download
Model tree No model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/Devstral-Small-2505-4bitOpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
mistral 11.7 GB alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF gguf permissive Facts Params not stated Size 11.7 GB Formats gguf Task text generation License Apache-2.0 permissive flip From: bartowski <huggingface.co/bartowski> Subject: alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF mistral 108 MB chatbench-mistral-7b safetensors permissive Facts Params not stated Size 108 MB Formats safetensors Task not tagged License Apache-2.0 permissive flip From: <huggingface.co/microsoft> Subject: chatbench-mistral-7b 23.6B params 47.2 GB DeepHermes-3-Mistral-24B-Preview safetensors permissive Facts Params 23.6B Size 47.2 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: NousResearch <huggingface.co/NousResearch> Subject: DeepHermes-3-Mistral-24B-Preview 24B params 51.6 GB Devstral-Small-2-24B-Instruct-2512 safetensors permissive Facts Params 24B Size 51.6 GB Formats safetensors Task not tagged License Apache-2.0 permissive flip From: <huggingface.co/mistralai> Subject: Devstral-Small-2-24B-Instruct-2512 24B params 15.1 GB Devstral-Small-2-24B-Instruct-2512-4bit safetensors permissive Facts Params 24B Size 15.1 GB Formats safetensors Task image text to text License Apache-2.0 permissive flip From: <huggingface.co/mlx-community> Subject: Devstral-Small-2-24B-Instruct-2512-4bit 24B params 20.9 GB Devstral-Small-2-24B-Instruct-2512-6bit safetensors permissive Facts Params 24B Size 20.9 GB Formats safetensors Task image text to text License Apache-2.0 permissive flip From: <huggingface.co/mlx-community> Subject: Devstral-Small-2-24B-Instruct-2512-6bit
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.mistralSubject: 
mistralai