alt.freeweights.mistral / Mistral-Small-3.1-24B-Instruct-2503-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.mistralSubject:

Mistral-Small-3.1-24B-Instruct-2503-4bit

Date: 2026-11-15Commit: 46135efSigned: 2DC28CC7B26A283B ✓

Model. Safetensors weights, 14.1 GB in all. Published by mlx-community under Apache-2.0.

mistral14.1GBMistral-Small-3.1-24B-Instruct-2503-4bitsafetensorspermissive
FactsParamsnot statedSize14.1 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit
# manifest sha256 3ee60985e268… · 14.1 GB · 16 files
$ fw verify ./Mistral-Small-3.1-24B-Instruct-2503-4bit mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit
From sourceHosted (signed)mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bitLast check: 2026-11-15 03:35 UTC

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

Fine-tune of Mistral-Small-3.1-24B-Base-2503.

Works with

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

Overview

Size
14.1 GB
Weights
14.1 GB (safetensors)
Parameters
not stated
Formats
safetensors
Task
not tagged
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/Mistral-Small-3.1-24B-Base-2503

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 03:35 UTCpassed

Model card

From the publisher at commit 46135ef. Shown as plain text with links; images open at the publisher.

mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit#

This model was converted to MLX format from prince-canuma/Mistral-Small-3.1-24B-Instruct-2503 using mlx-vlm version 0.1.19. Refer to the original model card for more details on the model.

Use with mlx#

pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

16 files · 14.1 GBWeights 14.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.62 KB1e11e8e6b9eb852a71eadd8fe191d4b9e329eb81308602dec19ab16da7e172b2
README.md1.01 KBaa1eedeaa4e2c0d4ddd28ef0152b46814927ede95be5dcd6070f5e6be1a6d79d
chat_template.json2.21 KBe7207a5d13b1596e314b2b0a34a6a5a74a9e2987e7d6acea47c3c05f32233bc6
config.json1.43 KB3c7cdd6f503a38e5c4306bb0618184e3ba5dc48fe7e681a2cc50260462e15d9b
generation_config.json116 B8e8cb26b98a0738d5ce154290725a4d7d65a577d3cfe586eb3cea4ebecf83105
model-00001-of-00003.safetensors5.37 GB6515ed40bbdea947a8b2958ec864c982178b770e75131b6dbcd97b2e9f18f2df
model-00002-of-00003.safetensors5.32 GB624d6de520be850882cd55fad28f5019e8f23fe56b8e9b1a3b92b464fe93db78
model-00003-of-00003.safetensors3.40 GB00dbb2cb245ef8151d18d833c827436bfb3e7d0a0e9050ca0d1a830c7e4863db
model.safetensors.index.json57.9 KB664a049408e8694e5867312145b74b1971ad5472061a1f176e0806dec9b3d21c
params.json768 B925d9c90e80dea268272b3af30cf6127b6ced8e165f8ba20ba09a2009adcddfb
preprocessor_config.json634 B0f1a312ed75c86bccdf65333b5b43507f597028d895dbb9cf9f16be9f87b52f1
processor_config.json162 B7e6736fb9d77a3b818eadc73e1a2b145a0502ea1bb29bc56b530ff4c74c6190d
special_tokens_map.json21.4 KBc98562eff7be177aafa0bf23cacb9c86549aef1c4c60e91931bded3d70fe6f8f
tekken.json14.8 MBc604f35d1035f534519622c0ec83fed6184978d4fdee92a5bd2a50bc05438094
tokenizer.json17.1 MBb76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
tokenizer_config.json198 KB85d2cc5ea2cddee01ddd36fe98a2eed62d85e78c8b049ea93ee0b2ae4c2c8e5e
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
46135ef3c5 pinned now2026-11-15 03:35 UTC16 files · 14.1 GB

Use it

$ fw get mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit
# manifest sha256 3ee60985e268… · 14.1 GB · 16 files
$ fw verify ./Mistral-Small-3.1-24B-Instruct-2503-4bit mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit.json --dir ./Mistral-Small-3.1-24B-Instruct-2503-4bit $ python3 fw.py verify ./Mistral-Small-3.1-24B-Instruct-2503-4bit ./mlx-community__Mistral-Small-3.1-24B-Instruct-2503-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit --revision 46135ef3c556bfed61013d8789bd26af02e416c4 --local-dir ./Mistral-Small-3.1-24B-Instruct-2503-4bit

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
aa1eedeaa4e2c0d4ddd28ef0152b46814927ede95be5dcd6070f5e6be1a6d79d
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: Mistral-Small-3.1-24B-Instruct-2503-4bitDate: 2026-11-15Commit: 46135efSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit
Pinned commit
46135ef3c556bfed61013d8789bd26af02e416c4
Manifest
Mistral-Small-3.1-24B-Instruct-2503-4bit.json · .minisig
Manifest sha256
3ee60985e2684b4fd4082c55946208d020f9488e9a9f5fd9b1e970f8dbb2b83e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:35 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit.json.minisig $ minisign -Vm Mistral-Small-3.1-24B-Instruct-2503-4bit.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/Mistral-Small-3.1-24B-Base-2503 · this model is a finetune 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/Mistral-Small-3.1-24B-Instruct-2503-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Mistral-Small-3.1-24B-Instruct-2503-4bit.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