CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-235B-A22B-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-235B-A22B-4bit

Date: 2026-11-15Commit: 72b19a1Signed: 2DC28CC7B26A283B ✓

Text generation model with 235.1B parameters. Safetensors weights, 132 GB in all. Published by mlx-community under Apache-2.0.

235.1B params132GBQwen3-235B-A22B-4bitsafetensorspermissive
FactsParams235.1BSize132 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-235B-A22B-4bit
# manifest sha256 ad758f74fa78… · 132 GB · 36 files
$ fw verify ./Qwen3-235B-A22B-4bit mlx-community/Qwen3-235B-A22B-4bit
From sourceHosted (signed)mlx-community/Qwen3-235B-A22B-4bitLast check: 2026-11-15 04:52 UTC
Get help

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

Quantized of Qwen3-235B-A22B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
132 GB
Weights
132 GB (safetensors)
Parameters
235.1B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
36, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-235B-A22B

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 04:52 UTCpassed

Model card

From the publisher at commit 72b19a1. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-235B-A22B-4bit#

This model mlx-community/Qwen3-235B-A22B-4bit was converted to MLX format from Qwen/Qwen3-235B-A22B using mlx-lm version 0.24.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-235B-A22B-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

36 files · 132 GBWeights 132 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 36 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md913 B27e4dd2796cb45da2d88ac586c7b38d1571f767a2ce445db26a4516626bbac6b
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
config.json1.19 KBb7257128bbd62e7478328d7f36a6065eaf9ce144d6127350c460e8e12b94fc28
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00026.safetensors5.04 GB0be299248c60e31f04bbd5d1e162f6c85fc87787a393af72ef3ed66a689bd671
model-00002-of-00026.safetensors5.14 GB41ddff7037306997380445b9b5ddbc463f211667708fe5f1ec61d3f7b93c61e6
model-00003-of-00026.safetensors5.10 GB406fecd40bab289e6838ddf9b83f4c52f2c8a33c78ced8e5f0434131ccc80131
model-00004-of-00026.safetensors5.14 GB21902e480f68ec03766566fa9842f5e5af58bb110b3cedc25969c3666a219574
model-00005-of-00026.safetensors5.14 GB51b663a793cf14c76d12b968a0e40728db6615d6df860a6203f57c583757a5ef
model-00006-of-00026.safetensors5.10 GB6813978048e72e1e49250ec24dbc05557f911283d76a45dc436f2107b53b3033
model-00007-of-00026.safetensors5.14 GB7781e5d1a0e1155306ebfb10e77e31fe86e64f4b314939cfd11e06c053e173a1
model-00008-of-00026.safetensors5.14 GB7450f5a7fabbea59ed9af20b1ca86a0d79302f8f956a69d6a47b062dae256ff4
model-00009-of-00026.safetensors5.10 GB80fdf26f401daabc8773c2baf92eb79848bb147e5d192a62e32a71976ac2a58a
model-00010-of-00026.safetensors5.14 GB99129c100b5581bc9720290e73de1701c4a7fceffb4f0183f85a5e9d532bb97b
model-00011-of-00026.safetensors5.14 GBddd3df9b5ee80838def65195aaee260fa6860e674895988a9ba2f2891a51bef1
model-00012-of-00026.safetensors5.10 GBd37e2739c62b6726869835cec626ba4b7cf97561ef32a76e04c6394f417f2750
model-00013-of-00026.safetensors5.14 GBf2b9a709ca5032487b3b5beff9681a33c16f87c0659e39e7d4e86fc5d6a02ee0
model-00014-of-00026.safetensors5.14 GBc6a1548ac7ba3ce7f9fb988e76b870188d64514c83070f5c28d51c9c521d67b8
model-00015-of-00026.safetensors5.10 GB609910fdc98f8f5c8bf0064c5ec02c6c060eff8344b55e00293452c86a7fa8b6
model-00016-of-00026.safetensors5.14 GB9601bb1ea93123dd84d7f16b6cbfe1d7236640c7c7cd3104545c59dbf790a90d
model-00017-of-00026.safetensors5.14 GBae4db8cc201c239e6911e65ff5c2e311b1e832eb2108b0e627a414363d406c65
model-00018-of-00026.safetensors5.10 GBa6c1f304466b89b590d4a0f5b230f65af9509c09764e1e35f19100b4f7a9666d
model-00019-of-00026.safetensors5.14 GB01cd7c239312ff2b334286e3ba6cefb9bcb68455fdae45adf4f1541955eb97ac
model-00020-of-00026.safetensors5.14 GB77b2495bf268ae7569615747009ca1a6533bc140960cd87b76917f3fc5b41535
model-00021-of-00026.safetensors5.10 GB581eac88b7a5d3cd4b6d547d25d59363e53ee8aa7b350d90bd35205795c60852
model-00022-of-00026.safetensors5.14 GB6ef1502b851416225f45e1b4eebc5babb2d3c29a3cc9ad130582891b4be2a30e
model-00023-of-00026.safetensors5.14 GB2c570c64e10cdc3ef4a836ab2daf381897a5ba7169ad71d426ab0b3e490356cf
model-00024-of-00026.safetensors5.10 GBf2f3462a179c31c528c9260e6c07442a1ab94d3761251fff1d4617908c8a7c0d
model-00025-of-00026.safetensors5.14 GB043d31b703451fe67ba0b5f0aa881ac9507b02a3ce8737e512f8a733991e5d44
model-00026-of-00026.safetensors4.05 GB63cab7b39ecd81a5bb637ac2b13a6b5595a7a0da87a256bfcdf1f9542e802bd1
model.safetensors.index.json234 KBe222a62574f20c1ea008289a6c688cd2b91d322e443a083b74e5a88fab790d4e
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json9.71 KB253153d0738ceb4c668d2eff957714dd2bea0b56de772a9fdccd96cbf517e6a0
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
72b19a1fe5 pinned now2026-11-15 04:52 UTC36 files · 132 GB

Use it

$ fw get mlx-community/Qwen3-235B-A22B-4bit
# manifest sha256 ad758f74fa78… · 132 GB · 36 files
$ fw verify ./Qwen3-235B-A22B-4bit mlx-community/Qwen3-235B-A22B-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/Qwen3-235B-A22B-4bit.json --dir ./Qwen3-235B-A22B-4bit $ python3 fw.py verify ./Qwen3-235B-A22B-4bit ./mlx-community__Qwen3-235B-A22B-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-235B-A22B-4bit --revision 72b19a1fe55594225acc8b693f2ca0dedf22c849 --local-dir ./Qwen3-235B-A22B-4bit
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/Qwen3-235B-A22B-4bit", revision="72b19a1fe55594225acc8b693f2ca0dedf22c849") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-235B-A22B-4bit", revision="72b19a1fe55594225acc8b693f2ca0dedf22c849", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-235B-A22B-4bit --revision 72b19a1fe55594225acc8b693f2ca0dedf22c849

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
27e4dd2796cb45da2d88ac586c7b38d1571f767a2ce445db26a4516626bbac6b
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.qwenSubject: Qwen3-235B-A22B-4bitDate: 2026-11-15Commit: 72b19a1Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-235B-A22B-4bit
Pinned commit
72b19a1fe55594225acc8b693f2ca0dedf22c849
Manifest
Qwen3-235B-A22B-4bit.json · .minisig
Manifest sha256
ad758f74fa7874a22d1d25f911e44ee8c7450bb9ba7a614ce302861e1efb7da5
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:52 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-4bit.json.minisig $ minisign -Vm Qwen3-235B-A22B-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

Qwen/Qwen3-235B-A22B · 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/Qwen3-235B-A22B-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-235B-A22B-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-235B-A22B-4bit

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF