CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.mistral / Mistral-Small-3.2-24B-Instruct-2506-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.mistralSubject:

Mistral-Small-3.2-24B-Instruct-2506-8bit

Date: 2026-11-15Commit: 1db8354Signed: 2DC28CC7B26A283B ✓

Text generation model with 23.6B parameters. Safetensors weights, 25.1 GB in all. Published by mlx-community under Apache-2.0.

23.6B params25.1GBMistral-Small-3.2-24B-Instruct-2506-8bitsafetensorspermissive
FactsParams23.6BSize25.1 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
# manifest sha256 33e97d8084ee… · 25.1 GB · 13 files
$ fw verify ./Mistral-Small-3.2-24B-Instruct-2506-8bit mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
From sourceHosted (signed)mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bitLast check: 2026-11-15 05:09 UTC
Run at homeGet help

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

Quantized of Mistral-Small-3.2-24B-Instruct-2506.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
25.1 GB
Weights
25.0 GB (safetensors)
Parameters
23.6B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
13, 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-3.2-24B-Instruct-2506

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 05:09 UTCpassed

Model card

From the publisher at commit 1db8354. Shown as plain text with links; images open at the publisher.

mlx-community/Mistral-Small-3.2-24B-Instruct-2506-q8#

This model mlx-community/Mistral-Small-3.2-24B-Instruct-2506-q8 was converted to MLX format from mistralai/Mistral-Small-3.2-24B-Instruct-2506 using mlx-lm version 0.25.2.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral-Small-3.2-24B-Instruct-2506-q8")

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

13 files · 25.1 GBWeights 25.0 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.30 KB281e4446c4ca0e6b84bba71ef96aae2ef29a2868e942d8ac356896f412268ff6
config.json1.08 KBa405580c2bcf8471002c1f9ebe0d51d608c1e2ce25961169f16db20170df4f71
generation_config.json135 Bac52ac4e326beae33b9dd33f5fca0301fc563e34becfe98ee210ee2b853d93bb
model-00001-of-00005.safetensors5.26 GB928bb554896f63bdb676834933f7c0edb171dfc7254df6c658e3c6f35156fb50
model-00002-of-00005.safetensors5.31 GBb8f724ca0b1b07261de107fe611151cb4eb1f2f9ad3c163a79a97e9b4a2d4c08
model-00003-of-00005.safetensors5.31 GB9775df5fc00e62886ba7738e140db6ff1eed454bab2612a3cff40dd0020dc0ee
model-00004-of-00005.safetensors5.31 GB0230cd3ae88619858ed34a06c9dda0a95587f15fa8360b8aa18e20c61fcf691e
model-00005-of-00005.safetensors3.84 GB757bc3dabc938ca681f4c10c6808b46a5bfd27010388d1110d34f9c1d2b269e4
model.safetensors.index.json93.3 KBbf9a1f3d6c0ffb2f3e4640772c4901270399149ea7e2395ce1dbf438db682695
special_tokens_map.json21.3 KB5bc5d1c106bf86895473568ef5211f3fde8415e6fdee039223d6db8ca52cbe01
tokenizer.json17.1 MBb76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
tokenizer_config.json198 KB70b26ab59c2c959a0dee2b0f6146a2e9d3c2b61b3995d6d584eb975f522b4c92
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1db835463e pinned now2026-11-15 05:09 UTC13 files · 25.1 GB

Use it

$ fw get mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
# manifest sha256 33e97d8084ee… · 25.1 GB · 13 files
$ fw verify ./Mistral-Small-3.2-24B-Instruct-2506-8bit mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
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-3.2-24B-Instruct-2506-8bit.json --dir ./Mistral-Small-3.2-24B-Instruct-2506-8bit $ python3 fw.py verify ./Mistral-Small-3.2-24B-Instruct-2506-8bit ./mlx-community__Mistral-Small-3.2-24B-Instruct-2506-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit --revision 1db835463eb0f953019af1048077b90403b70424 --local-dir ./Mistral-Small-3.2-24B-Instruct-2506-8bit
transformersLoad 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/Mistral-Small-3.2-24B-Instruct-2506-8bit", revision="1db835463eb0f953019af1048077b90403b70424") model = AutoModelForCausalLM.from_pretrained("mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit", revision="1db835463eb0f953019af1048077b90403b70424", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit --revision 1db835463eb0f953019af1048077b90403b70424
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
281e4446c4ca0e6b84bba71ef96aae2ef29a2868e942d8ac356896f412268ff6
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-3.2-24B-Instruct-2506-8bitDate: 2026-11-15Commit: 1db8354Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
Pinned commit
1db835463eb0f953019af1048077b90403b70424
Manifest
Mistral-Small-3.2-24B-Instruct-2506-8bit.json · .minisig
Manifest sha256
33e97d8084eee05065820d66c9d97008508ce9c9073f13a6ff2410e569318053
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:09 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit.json.minisig $ minisign -Vm Mistral-Small-3.2-24B-Instruct-2506-8bit.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-3.2-24B-Instruct-2506 · 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/Mistral-Small-3.2-24B-Instruct-2506-8bit
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-3.2-24B-Instruct-2506-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit

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-2512-4bit
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-6bit