CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-235B-A22B-Thinking-2507-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-235B-A22B-Thinking-2507-4bit

Date: 2026-11-15Commit: f83ccd4Signed: 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-Thinking-2507-4bitsafetensorspermissive
FactsParams235.1BSize132 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit
# manifest sha256 0dbb263cb875… · 132 GB · 38 files
$ fw verify ./Qwen3-235B-A22B-Thinking-2507-4bit mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit
From sourceHosted (signed)mlx-community/Qwen3-235B-A22B-Thinking-2507-4bitLast check: 2026-11-15 04:45 UTC
Get help

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

Quantized of Qwen3-235B-A22B-Thinking-2507.

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
38, 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-Thinking-2507

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 04:45 UTCpassed

Model card

From the publisher at commit f83ccd4. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit#

This model mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit was converted to MLX format from Qwen/Qwen3-235B-A22B-Thinking-2507 using mlx-lm version 0.26.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit")

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

38 files · 132 GBWeights 132 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 38 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.02 KBdebe2f312c60a404b62e9ab2a0d01fa7dc889b07efedbf870bb1ace5aeb9d1e8
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.05 KB3802169b2a02b81e6adb7ab4f64f91ff02db753c8c3a64a01c35192d3a61d8d7
config.json1.19 KB03c6a09125e6b0a558d739a3bfae90cebdce684bb8641aa94d26ca0e0c3d83d6
generation_config.json239 B2325da0f15bb848e018c5ae071b7943332e9f871d6b60e2ed22ca97d4cb993d2
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00026.safetensors5.04 GB307a0b6c6500e3d28978433588985390e41dc5f0e8fd4f64ac5a80b043454314
model-00002-of-00026.safetensors5.14 GBed4566378e98cc9888fa727a6f230d2ce0dab6c9706ea5cc97cfee753559603a
model-00003-of-00026.safetensors5.10 GB2bd81d60d1c90ed79ec6e8e568f339b1bd4097b7c0e82ae0dfa65661ae0a254f
model-00004-of-00026.safetensors5.14 GB05fb42b2a9f3279f3ed269ac47b80de1d5de4660fb86d46b16974a28119d91b8
model-00005-of-00026.safetensors5.14 GBb2c4f51ebf7066f59b3d33f2ecf98e8ac136d73cb7dd1712a14a2f7c7e346c08
model-00006-of-00026.safetensors5.10 GBe49e457b409432cc7c31d61bfa37d49c2a2ad47d6800695cba7206c6f53b139f
model-00007-of-00026.safetensors5.14 GBe52f04a1cdb8fdc123d1189751a48fbfc886eb572ebc2c68e273eb51b1a00a29
model-00008-of-00026.safetensors5.14 GBe0660c993e8c3db0b8675187bdee21cf07fe1e7c065efbe246943a139e7494e0
model-00009-of-00026.safetensors5.10 GB38b432683fd3ab2f97fa5b51054de3fe1134a63493c05b3c18ceadd3025ac0ad
model-00010-of-00026.safetensors5.14 GB2e376dc3377012658b931e54ca962246fa0def891033c9ebe0073aedb8406a65
model-00011-of-00026.safetensors5.14 GBc73a9b93e6dfa3d74dd4b27499b1c9b48d94b6b559399bf3ea047c4a36ffee59
model-00012-of-00026.safetensors5.10 GB8cf9cc53ff3d13c724872a10c2e6fb1c3de19f4be19e9b22c3db53fc249cc2b4
model-00013-of-00026.safetensors5.14 GB9871bc27af851b097a51c8f79e0593697de0efdb8f7e362843b3a2b43ef9011e
model-00014-of-00026.safetensors5.14 GBf4720cc8ef925a77b896b45b65e88ead8a4ba6a984bbb96da6b30eb36f9e635c
model-00015-of-00026.safetensors5.10 GBe5377e9459fcead77a2dc1d2ba23b5468a89e6907d0293e6f577c128ae83fe01
model-00016-of-00026.safetensors5.14 GB1a865974332c4f7978201f1d741ab40121e9790becb207bb9b2a16830b2d4e60
model-00017-of-00026.safetensors5.14 GBe5795147411696b78989d2eacaf775d5b8c6ba75ed795628442e6decbc175e50
model-00018-of-00026.safetensors5.10 GB12cda121defaa73ad080d80893214c5db84d1b96a6111dc0773fd95e340b085d
model-00019-of-00026.safetensors5.14 GB3b119baa24f11eee7b471ad34a98869877622b1d080a10f4d490902f7e257e21
model-00020-of-00026.safetensors5.14 GB8c0d1f8ee23c18a5b797a60b6ef6ebb0a63f8de8d22b3223ee5185190793f5e0
model-00021-of-00026.safetensors5.10 GBcd07fb774ff3b0893e7a93c4dce5c518d4980a245f7375e678cb6ebd0545a86c
model-00022-of-00026.safetensors5.14 GB7548fc06c041249b22ba57291209385868741af2b961cb16a4f8ec51cf52ca2f
model-00023-of-00026.safetensors5.14 GB414e3f16dfad48636f5a1f4d071f478a991afbaf22a4605f4cc53012ffb1285a
model-00024-of-00026.safetensors5.10 GB3c9ce585d696f0ae4557663bfc4c6304b01e5412ec21f84374069de374f66f66
model-00025-of-00026.safetensors5.14 GB365f9e2471b5b674278d247e57656c730931d671518232d9e8ca5ecf5b022107
model-00026-of-00026.safetensors4.05 GB85eec40f3c0adf75549faf7b8af02c1f47c57988c1d7c4b74d8a2af1918b3e3d
model.safetensors.index.json234 KB9172a06e3f564e1a930a311100eee562dbf038473b0d30d9ad1063070c1841b4
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.40 KB355f2b4e5bad7b01f11ef6cb68ebc176f61b95c3276092ea225b1bea0e01e95c
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f83ccd4ba9 pinned now2026-11-15 04:45 UTC38 files · 132 GB

Use it

$ fw get mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit
# manifest sha256 0dbb263cb875… · 132 GB · 38 files
$ fw verify ./Qwen3-235B-A22B-Thinking-2507-4bit mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit
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-Thinking-2507-4bit.json --dir ./Qwen3-235B-A22B-Thinking-2507-4bit $ python3 fw.py verify ./Qwen3-235B-A22B-Thinking-2507-4bit ./mlx-community__Qwen3-235B-A22B-Thinking-2507-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit --revision f83ccd4ba9f620edcaea2eb1b9cd78101786b96d --local-dir ./Qwen3-235B-A22B-Thinking-2507-4bit
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-Thinking-2507-4bit", revision="f83ccd4ba9f620edcaea2eb1b9cd78101786b96d") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit", revision="f83ccd4ba9f620edcaea2eb1b9cd78101786b96d", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit --revision f83ccd4ba9f620edcaea2eb1b9cd78101786b96d

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
debe2f312c60a404b62e9ab2a0d01fa7dc889b07efedbf870bb1ace5aeb9d1e8
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-Thinking-2507-4bitDate: 2026-11-15Commit: f83ccd4Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit
Pinned commit
f83ccd4ba9f620edcaea2eb1b9cd78101786b96d
Manifest
Qwen3-235B-A22B-Thinking-2507-4bit.json · .minisig
Manifest sha256
0dbb263cb87544a14c1e1a2b33fe2665085a53acd6b8959562b35e57eafad01b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:45 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit.json.minisig $ minisign -Vm Qwen3-235B-A22B-Thinking-2507-4bit.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-Thinking-2507 · 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-Thinking-2507-4bit
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-Thinking-2507-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-235B-A22B-Thinking-2507-4bit

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