alt.freeweights.mistral / mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.mistralSubject:

mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16

Date: 2026-11-15Commit: 0f28858Signed: 2DC28CC7B26A283B ✓

Image text to text model with 24B parameters. Safetensors weights, 48.1 GB in all. Published by mlx-community under Apache-2.0.

24B params48.1GBmistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16safetensorspermissive
FactsParams24BSize48.1 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
# manifest sha256 127cdbe24b51… · 48.1 GB · 23 files
$ fw verify ./mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16 mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
From sourceHosted (signed)mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16Last check: 2026-11-15 05:13 UTC

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

Overview

Size
48.1 GB
Weights
48.0 GB (safetensors)
Parameters
24B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
23, 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 05:13 UTCpassed

Model card

From the publisher at commit 0f28858. Shown as plain text with links; images open at the publisher.

mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16#

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/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

23 files · 48.1 GBWeights 48.0 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 23 files with their sha256
FileSizesha256
.gitattributes1.62 KB1e11e8e6b9eb852a71eadd8fe191d4b9e329eb81308602dec19ab16da7e172b2
CHAT_SYSTEM_PROMPT.txt2.37 KB35e9942fc2a95dca58e4ce6484515f16a798f718aad0ce0b2e83ba0887f53b29
README.md825 Bce1ceeb23b788cb8b6af6ac9d9289b0bb8987f605e3f5615a95e1e10c48106c8
VIBE_SYSTEM_PROMPT.txt1.81 KBc55c3592065d1786b75e82fc0fe05ac4c4940b473e77799c8abb75e439a15556
chat_template.jinja5.62 KB4045652eb06390165d37ca4bfb5c88c4b021b74c516a043557d70db9522659e0
config.json2.42 KB5c291164ce3962eca0f8aebfc41caebf23c61adf0070e491064af5e73102a5fe
generation_config.json175 Bc5ee59a086c5504838db2a66cafdf04d10aac11cb021dd4e92a15946645c2dda
model-00001-of-00010.safetensors5.22 GBb20e1e64ba7940d96473d80fe8c80b8759c4ec4d01b0635ca1a74bca394053fa
model-00002-of-00010.safetensors5.22 GBb3a512f893571eb0e817365d3126a48cfb96943419bf5ae6478ab7103b5ec0c1
model-00003-of-00010.safetensors5.22 GBe23caf273b60879e5ccd784471db7c20b14ed6d14fb302cdd5a7ce61a3d65e67
model-00004-of-00010.safetensors5.12 GB893a1d1023aa333e8fdc46207bf67928fb5c02f723b8184576145f5df62a33e3
model-00005-of-00010.safetensors5.22 GB7e9ea694687a0ab5ac49bb7b17362a9c32353edf36751515da0ccc8fc05ef802
model-00006-of-00010.safetensors5.22 GBd1ec172629873e479a32dfd03629a416e9fe61174280acd65ec79f0679bbfe89
model-00007-of-00010.safetensors5.12 GB235abbd12da4ba29ce632fc39c58cb86bbad37964ff2ad319790c45b7586b9ef
model-00008-of-00010.safetensors5.22 GB8d100ace04f2fa657657bfa4546da8d04acd80e6497c7fe3733252c78ff1ec59
model-00009-of-00010.safetensors5.12 GBb89e84c5ab4f524f3ec596e71c5092c52f8a30ec63e2d792ebe06823cb74129d
model-00010-of-00010.safetensors1.34 GB9205655e837a15dc8fd6ab19a22758319ab9fd442245b3694b7765177ac235d9
model.safetensors.index.json63.1 KB4ae5487dda87f4cb95a38f7ce966b69911a33b56418e944bbf03d81c54c10daf
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
0f2885850a pinned now2026-11-15 05:13 UTC23 files · 48.1 GB

Use it

$ fw get mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
# manifest sha256 127cdbe24b51… · 48.1 GB · 23 files
$ fw verify ./mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16 mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16.json --dir ./mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16 $ python3 fw.py verify ./mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16 ./mlx-community__mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16 --revision 0f2885850a904d30a8855136d025969eb1b8a639 --local-dir ./mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
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/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16", revision="0f2885850a904d30a8855136d025969eb1b8a639") model = AutoModelForImageTextToText.from_pretrained("mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16", revision="0f2885850a904d30a8855136d025969eb1b8a639", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16 --revision 0f2885850a904d30a8855136d025969eb1b8a639

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
ce1ceeb23b788cb8b6af6ac9d9289b0bb8987f605e3f5615a95e1e10c48106c8
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: mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16Date: 2026-11-15Commit: 0f28858Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
Pinned commit
0f2885850a904d30a8855136d025969eb1b8a639
Manifest
mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16.json · .minisig
Manifest sha256
127cdbe24b51ba0b2d81ca767338d7870909c661c2d30f4b7da978b2f18ca6af
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:13 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16.json.minisig $ minisign -Vm mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16.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/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-BF16.json. Provenance. Takedown history: none.
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-2512-4bit
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-6bit