CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.mistral / Devstral-Small-2-24B-Instruct-2512-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.mistralSubject:

Devstral-Small-2-24B-Instruct-2512-4bit

Date: 2026-11-15Commit: 9722855Signed: 2DC28CC7B26A283B ✓

Image text to text model with 24B parameters. Safetensors weights, 15.1 GB in all. Published by mlx-community under Apache-2.0.

24B params15.1GBDevstral-Small-2-24B-Instruct-2512-4bitsafetensorspermissive
FactsParams24BSize15.1 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
# manifest sha256 8a03b299cf12… · 15.1 GB · 16 files
$ fw verify ./Devstral-Small-2-24B-Instruct-2512-4bit mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
From sourceHosted (signed)mlx-community/Devstral-Small-2-24B-Instruct-2512-4bitLast check: 2026-11-15 04:37 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of Devstral-Small-2-24B-Instruct-2512.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
15.1 GB
Weights
15.1 GB (safetensors)
Parameters
24B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
16, 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-2-24B-Instruct-2512

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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:37 UTCpassed

Model card

From the publisher at commit 9722855. Shown as plain text with links; images open at the publisher.

mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit#

This model was converted to MLX format from mistralai/Devstral-Small-2-24B-Instruct-2512 at revision c599e8e56f3f9110e97f0dc0450ce248e3334d84.

It was generated from the current mlx-vlm source checkout on the JarvisLabs conversion instance.

Use with mlx-vlm#

pip install -U mlx-vlm
mlx_vlm.generate --model mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

16 files · 15.1 GBWeights 15.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.62 KB1e11e8e6b9eb852a71eadd8fe191d4b9e329eb81308602dec19ab16da7e172b2
CHAT_SYSTEM_PROMPT.txt2.37 KB35e9942fc2a95dca58e4ce6484515f16a798f718aad0ce0b2e83ba0887f53b29
README.md798 Baa90cce4886622cb606a813ce0f1ba6f6fa044689d0a623df9dd7471d70b9005
VIBE_SYSTEM_PROMPT.txt1.81 KBc55c3592065d1786b75e82fc0fe05ac4c4940b473e77799c8abb75e439a15556
chat_template.jinja5.32 KBed825380b678dad25046e0a92ef5c64a57178ccaba7e780b5ed581e91a4fd6ac
config.json2.31 KB9d3d76706bab9e3515a1603514a515e60ba844c78b7c447604560262130bdfcb
generation_config.json175 Bc5ee59a086c5504838db2a66cafdf04d10aac11cb021dd4e92a15946645c2dda
model-00001-of-00003.safetensors5.35 GBbf03240339489cbf7582654c237b7c7bba729640eb5957fbb8918b889d9a8e91
model-00002-of-00003.safetensors5.31 GB1adbf960fd4eee50836d54683dd0a8915976ec57a6326cfa0588238fa6c6e69f
model-00003-of-00003.safetensors4.44 GB562933b8e4840869a912bf0d9ba1b53a7ebd13619f299342d0c0e2229b95a639
model.safetensors.index.json119 KB3f4e2d4721509e89ae2415389ecb021bc618aa547dfe3342f997ed3481c4daf9
params.json1.19 KB1618da0d6f897e074ff7ec4b1047b5d2e8a1a4aa1fab41e26fc88f3b5b94d2aa
processor_config.json821 Bcb1dc0b2c1a2da025f50df0f1516bc7018aaae98916b19c0ced6f189a7dd700b
tekken.json16.8 MB600bb27946565481ecf51ba8aee252e49b9a68507866080ac9c30185bb312843
tokenizer.json17.1 MB99cf274236c60277fcfad861a5a1007518687ad06ba8938760f50b55ffa0b1ef
tokenizer_config.json21.2 KBd11b71c3d855b030fb174bc8bf20542ccaf8281c7897d8074942a717eb0f11e4
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
97228558fc pinned now2026-11-15 04:37 UTC16 files · 15.1 GB

Use it

$ fw get mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
# manifest sha256 8a03b299cf12… · 15.1 GB · 16 files
$ fw verify ./Devstral-Small-2-24B-Instruct-2512-4bit mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit.json --dir ./Devstral-Small-2-24B-Instruct-2512-4bit $ python3 fw.py verify ./Devstral-Small-2-24B-Instruct-2512-4bit ./mlx-community__Devstral-Small-2-24B-Instruct-2512-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit --revision 97228558fcbdd1adefd39d515155db3a894b37f7 --local-dir ./Devstral-Small-2-24B-Instruct-2512-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit", revision="97228558fcbdd1adefd39d515155db3a894b37f7") model = AutoModelForImageTextToText.from_pretrained("mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit", revision="97228558fcbdd1adefd39d515155db3a894b37f7", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit --revision 97228558fcbdd1adefd39d515155db3a894b37f7
Run at home

License

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
aa90cce4886622cb606a813ce0f1ba6f6fa044689d0a623df9dd7471d70b9005
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: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.mistralSubject: Devstral-Small-2-24B-Instruct-2512-4bitDate: 2026-11-15Commit: 9722855Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
Pinned commit
97228558fcbdd1adefd39d515155db3a894b37f7
Manifest
Devstral-Small-2-24B-Instruct-2512-4bit.json · .minisig
Manifest sha256
8a03b299cf12d9223b66bc94948791f43c77ed1d2c6565be44ac653ca02c1759
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:37 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit.json.minisig $ minisign -Vm Devstral-Small-2-24B-Instruct-2512-4bit.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

Parent

mistralai/Devstral-Small-2-24B-Instruct-2512 · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Devstral-Small-2-24B-Instruct-2512-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit

Related models

All of alt.freeweights.mistral →
From: bartowski <huggingface.co/bartowski>Subject: alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF
From: microsoft <huggingface.co/microsoft>Subject: chatbench-mistral-7b
From: NousResearch <huggingface.co/NousResearch>Subject: DeepHermes-3-Mistral-24B-Preview
From: mistralai <huggingface.co/mistralai>Subject: Devstral-Small-2-24B-Instruct-2512
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-6bit
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-8bit