CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-235B-A22B-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-235B-A22B-8bit

Date: 2026-11-15Commit: 636d253Signed: 2DC28CC7B26A283B ✓

Text generation model with 235.1B parameters. Safetensors weights, 250 GB in all. Published by mlx-community under Apache-2.0.

235.1B params250GBQwen3-235B-A22B-8bitsafetensorspermissive
FactsParams235.1BSize250 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-235B-A22B-8bit
# manifest sha256 e50ccbfdbcab… · 250 GB · 58 files
$ fw verify ./Qwen3-235B-A22B-8bit mlx-community/Qwen3-235B-A22B-8bit
From sourceHosted (signed)mlx-community/Qwen3-235B-A22B-8bitLast check: 2026-11-15 05:06 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
250 GB
Weights
250 GB (safetensors)
Parameters
235.1B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
58, 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 05:06 UTCpassed

Model card

From the publisher at commit 636d253. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-235B-A22B-8bit#

This model mlx-community/Qwen3-235B-A22B-8bit 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-8bit")

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

58 files · 250 GBWeights 250 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 58 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md913 Bea75226af878256fbf86da758eb60d12a516eda2eac4c67ffb729f5b245ec015
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
config.json1.19 KBa9bc632a31fc6b92be456099a4696e75a4f3ef1732456998802670da443734b7
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00048.safetensors5.09 GB435092c27d7257b24d8c01cbbf99cec5cbecbc216da6ad7a2a7d65c148dd596a
model-00002-of-00048.safetensors5.29 GB25daa1799d16bdf91a01e78d97cdcbff018e6eda70c0131ebac4a565f0c92d6d
model-00003-of-00048.safetensors5.29 GB7993a4c634e082840dfbe82a7cd5d4aa6e137b81dbf593e91338d1f40592079f
model-00004-of-00048.safetensors5.29 GB1105ceda5a55bee50e4f4b178a82fab16111e449bf22687539fde0a5a500a243
model-00005-of-00048.safetensors5.29 GBc1062c7b091daa85a2e42c96aa35f0accdc26669f207ca35962940d74487e499
model-00006-of-00048.safetensors5.29 GB3b972e7556bd8e232fa54e500df577be961ca88005f60fd6db13058feb85b7e8
model-00007-of-00048.safetensors5.29 GB81c971d9bd7c395c7cf564339804faadb3d0a7651e0d3c065b1fc573145ae75d
model-00008-of-00048.safetensors5.29 GB90af5168e985879b8b26f8fe94488d027dc91ab45f0c3825fdcddf4107ff1a0a
model-00009-of-00048.safetensors5.29 GB7fc29658aff61772afcf9db0d287fd1d4daa4d4ee9d94c0b36c8c11da66e9147
model-00010-of-00048.safetensors5.29 GB0d32085d130933d37bfab6ac65f925fc2f279ea0fab6cb635080af8bcfc5b380
model-00011-of-00048.safetensors5.29 GB58b0c90e3dd2536a7f71138e92578f19c591d0da168cf5efa4a8614e8f547628
model-00012-of-00048.safetensors5.29 GBe0d6e34424cb987fe135df1c6cd060aa625e4ca6e64dbb5e7bfabaae9084a770
model-00013-of-00048.safetensors5.29 GBf31ebf6e30969d3e5fa694a01a7b9da80b3f1adc3d8995e6ecb50c409871898c
model-00014-of-00048.safetensors5.29 GB89ebf60a8486b01a95810edd054de8e5ef206e1f2d462593d1105719cf2fb820
model-00015-of-00048.safetensors5.29 GBaf5bb76d077aa6c35c9b5114837cf1be9a7049a4d2848e38a4ef62fc2eb061a1
model-00016-of-00048.safetensors5.29 GBce92d4c13755f47fff10402670af9460c51260d38524cded71f1238e27bce574
model-00017-of-00048.safetensors5.29 GBba001a2d405979ff2820fc08f9fd75b6a4fb6c81fb1a250bf8d9cf50468f4967
model-00018-of-00048.safetensors5.29 GB95c69dd451180a4d01e2e5a8eba019c8d26681712fcc052ed75bbf945e53e546
model-00019-of-00048.safetensors5.29 GBc130939abb0a62cd0fecf08bda6ae64596f8d3a472372ed9c5d951f9425f8c7c
model-00020-of-00048.safetensors5.29 GB0fe5e0d8e8ebf48aaa62d636462d8d6bef167e66c237235382dca2dfc37ef0f9
model-00021-of-00048.safetensors5.29 GB985489d2c09c1e7066382fb862216c3b63440761f3261b4e8a3df1e1274e0be0
model-00022-of-00048.safetensors5.29 GB763a9897ee0e96847f064f0c0437edcecb6b2f95935bb8560e5a7a37ce764132
model-00023-of-00048.safetensors5.29 GB90b7d6ae92e601e15898cb42eb66cca19e8d036e98ac7210e40b537b82223738
model-00024-of-00048.safetensors5.29 GB73ee7fb5c73da3c1fb352256e1a1dc8a989c8f051a2941a6eab6ada2f84cbe9e
model-00025-of-00048.safetensors5.29 GB645907ba233fb7b5f5ea57d47049d3535c53ae363fe786193dba9d6bf6d82bbd
model-00026-of-00048.safetensors5.29 GBdf7f0cd92bc86f198d7a9474653f74750a60649cef4cfe6ed2b5b02ccf51455d
model-00027-of-00048.safetensors5.29 GB710a01d3dd0fb40ccfc02630284cbe590c3d07620553e45a6c76c8e983445e86
model-00028-of-00048.safetensors5.29 GB3dae25903d1c14c2d6953cf6b05e3e06533c05794aa28465d9e96028c576c577
model-00029-of-00048.safetensors5.29 GB5684276345e576ffc346562a9f724ee0b464242c1ed18fede4d3b93311b0c1a1
model-00030-of-00048.safetensors5.29 GBce0450a56926c69bf2fc94e67c98ac3434ff681c849bdbb0f078337e42477fe6
model-00031-of-00048.safetensors5.29 GB3c613690100b406b4e64cd692077a5cede95ddd950741b6e871a679477c5ee7a
model-00032-of-00048.safetensors5.29 GB0b1874340c3662e2719b8135dfce9ae39b7c59e4fc07615cb69d5120bbaae43e
model-00033-of-00048.safetensors5.29 GBaaf54f91f20d255e2c6f129e7ae356d8540a5f69188cc0d0d335c9f6005da5ea
model-00034-of-00048.safetensors5.29 GBca5ed46f615fd0dc1995fca9f4332fdb333ba83e8b3ff2b0e2d94e1dfca0280d
model-00035-of-00048.safetensors5.29 GB06393d745f92c9ba117dcefb80e8458e70c07474fb6ea7429e90a072fcc10f20
model-00036-of-00048.safetensors5.29 GB7299228be319267ffecc32071109f4fdde068e0f3aca11fa6203e54dd2e712cf
model-00037-of-00048.safetensors5.29 GBab6211fbbd31b8dac2abab0278f1e396cfe24023d9485b07f8e593bc63485709
model-00038-of-00048.safetensors5.29 GBb4bdf38cab92219e25f6bc224ff666fde310b8b5d383ba4a2ac0c534a25a7b3d
model-00039-of-00048.safetensors5.29 GBedd89e79487b530cdce0a4221a428eb1e23838594ce51090c27da69b5f58545c
model-00040-of-00048.safetensors5.29 GB41ba6004e2f3accc74756d9d19fc94943c3d62a52c60aa62eaef49dcb23359e7
model-00041-of-00048.safetensors5.29 GB9b55e7eaf24b71ea4f70f80469f6c1f97824aaaef70a74284d92c30d9857a019
model-00042-of-00048.safetensors5.29 GB164b9f22b61bc31ad242ef76a0146a5a6106dac139ae609ed529147b2f74f6e6
model-00043-of-00048.safetensors5.29 GBc4dd380d4446d56bd0c677a108b11970513b29438939a252890c1fbf9d4ab9c0
model-00044-of-00048.safetensors5.29 GB136fd2848ea3b555f0f2c1c2913ddcbfbd4b9833a884135982cc5cd3202d0e6d
model-00045-of-00048.safetensors5.29 GB164ef66bf13002ea908479b7b4960fb74bae3bc578c0e7416420eea37c591982
model-00046-of-00048.safetensors5.29 GBc17f12b4448065e532fc973abba79566c0ceb9fb8d623d3f043a8b1f611ff4d1
model-00047-of-00048.safetensors5.29 GBae61fdfd3b42805c73e8e04d2f13b5daf1e8902b641e28c157ed00d6b0cb09dc
model-00048-of-00048.safetensors1.52 GBadce626e1be8abf2f6740f5afce84c18b1742d57d4e4df2cf17d88faac1f113b
model.safetensors.index.json234 KBf9ffa21e6fa873f65c32c212aac3a6f041aa343e12f14e2708f71ecc9cdaf261
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
636d25324d pinned now2026-11-15 05:06 UTC58 files · 250 GB

Use it

$ fw get mlx-community/Qwen3-235B-A22B-8bit
# manifest sha256 e50ccbfdbcab… · 250 GB · 58 files
$ fw verify ./Qwen3-235B-A22B-8bit mlx-community/Qwen3-235B-A22B-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/Qwen3-235B-A22B-8bit.json --dir ./Qwen3-235B-A22B-8bit $ python3 fw.py verify ./Qwen3-235B-A22B-8bit ./mlx-community__Qwen3-235B-A22B-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-235B-A22B-8bit --revision 636d25324d5dc87e38503fb36072e7c37c65c789 --local-dir ./Qwen3-235B-A22B-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/Qwen3-235B-A22B-8bit", revision="636d25324d5dc87e38503fb36072e7c37c65c789") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-235B-A22B-8bit", revision="636d25324d5dc87e38503fb36072e7c37c65c789", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-235B-A22B-8bit --revision 636d25324d5dc87e38503fb36072e7c37c65c789

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
ea75226af878256fbf86da758eb60d12a516eda2eac4c67ffb729f5b245ec015
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-8bitDate: 2026-11-15Commit: 636d253Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-235B-A22B-8bit
Pinned commit
636d25324d5dc87e38503fb36072e7c37c65c789
Manifest
Qwen3-235B-A22B-8bit.json · .minisig
Manifest sha256
e50ccbfdbcabe8d9261efa6d9be2263ae20ac22863effd2035e2930a0ff757a5
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:06 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-8bit.json.minisig $ minisign -Vm Qwen3-235B-A22B-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

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-8bit
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-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-235B-A22B-8bit

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