CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-235B-A22B-Instruct-2507-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-235B-A22B-Instruct-2507-8bit

Date: 2026-11-15Commit: 9704289Signed: 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-Instruct-2507-8bitsafetensorspermissive
FactsParams235.1BSize250 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit
# manifest sha256 0b9310d97ab8… · 250 GB · 60 files
$ fw verify ./Qwen3-235B-A22B-Instruct-2507-8bit mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit
From sourceHosted (signed)mlx-community/Qwen3-235B-A22B-Instruct-2507-8bitLast check: 2026-11-15 05:11 UTC
Get help

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

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

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
60, 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-Instruct-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 05:11 UTCpassed

Model card

From the publisher at commit 9704289. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit#

This model mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit was converted to MLX format from Qwen/Qwen3-235B-A22B-Instruct-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-Instruct-2507-8bit")

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

60 files · 250 GBWeights 250 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 60 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.02 KB571fe26ed4b0791757f2d20b562f5a1e7ed2ff909163305dd0a0a7347916f477
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.04 KB40c21f34cf67d8c760ef72f8ad3ae5afad514299d4b06e91dd9a8d705af7b541
config.json1.19 KBe3abec5a8d1270c50fa1d300b9db4aa068571f2af95911f531baae67cd990fcd
generation_config.json238 B835fffe355c9438e7a25be099b3fccaa98350b83451f9fd2d99512e74f1ade48
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00048.safetensors5.09 GBfcb897d25a09e5ac3ced1a6cebe9ba0184469790debd3637f0c56919454099eb
model-00002-of-00048.safetensors5.29 GB2895a0cf01167c03c5ab655adf1242e5e9400987d1ea88c8aa7667f9e98f649e
model-00003-of-00048.safetensors5.29 GB1029ccf3a9deac933e28a9413f590f64c96e69225ed3e1e0e377cf50d4bb22ce
model-00004-of-00048.safetensors5.29 GB57f7f6d9a7cd89efc9ef64f1925cc97aaf9bcdbf9f4f35f159eada7e5ad821ab
model-00005-of-00048.safetensors5.29 GB3386fe4394286ca03518e362dc32b1d8fe8e1b27c28c3f5024698feaa7dfde22
model-00006-of-00048.safetensors5.29 GB1053656e15d82c0827d2fabf4fe476b0d3734653693c9d140a974356c268c90e
model-00007-of-00048.safetensors5.29 GB485dce9921569716c6d4629ac0a76798315c87d196319d991c3484731fc79f3b
model-00008-of-00048.safetensors5.29 GB1e053508b7609ec509988696c5c0a44a0f4fdb57e9276475b4c005f55176bc29
model-00009-of-00048.safetensors5.29 GB16ebb8d2c9f1bbb8b7fe1dd78759bca572e0945e7fdc8c279726d767a4da2eb2
model-00010-of-00048.safetensors5.29 GB0bb01c28f73dc37e37cc75da08c5b6a433b81907929cad3aca6f07dd3909147c
model-00011-of-00048.safetensors5.29 GB2078f2f461c39bd1b6c153cba07f01feebcce61ff0134c18237deef8bc89d8c6
model-00012-of-00048.safetensors5.29 GB78b3bc2d5fc5339e007a4f89bab75af75dddfb916aee3f20e174670f88cada87
model-00013-of-00048.safetensors5.29 GBef08d8b555ffe152c828d2cca507bf80347dbbe379eb525299a8994746535e93
model-00014-of-00048.safetensors5.29 GB897c51927909cc6c65d71b7b66653bd50d3dc42baec30ddbaf4e6f8a46bc4725
model-00015-of-00048.safetensors5.29 GB919a2c62346be57102b280050ef1e9062f2fa8ad0ddb578c6ed9f3d5c77df5ac
model-00016-of-00048.safetensors5.29 GBe9a70c649d966def8fb5161915736fa28baa4b4d9c183de937f401e6e320ac47
model-00017-of-00048.safetensors5.29 GB483f28cfba3e9488b49e1f17a3cfb34af0608442ee136dbb894f7b2168a22bff
model-00018-of-00048.safetensors5.29 GBc8695fe68ed3378e0b9915fb198bf82525aa93fffab3d199a4f09dd11b31fb58
model-00019-of-00048.safetensors5.29 GBa82d87aa3e4b41a2eb12b3393ac572a330adad4f177e36a5ae8482e635b87597
model-00020-of-00048.safetensors5.29 GB2b94481fa51b242d2e4991a01219083ea1f44a1df979c5af80c2dc4aca0be26e
model-00021-of-00048.safetensors5.29 GB2f64068bd77fd529a0280ab389aeaddd0000a71c6b4e0dc4c103a323a8e69c4e
model-00022-of-00048.safetensors5.29 GBf2046bb60dba6e439cacf122dee277233f9ab4cbeb977aa820a9e010750d6b66
model-00023-of-00048.safetensors5.29 GBa3994eec50d0edb2eddff689665854c9f034380c9886ed1f0329d603e7ec2ab3
model-00024-of-00048.safetensors5.29 GB4747ca480cd8e07fea930756d81b6ec8b2d14e5e2f46eeb4ed25846e77cf7ea9
model-00025-of-00048.safetensors5.29 GB931a344ea621f40541a5753b2248c91c6615b30e491797ec3d67ccfcdefbd639
model-00026-of-00048.safetensors5.29 GB100f70ab086025913b51b23fbc871307bd00fe0e2f70555a2dc99de31052a812
model-00027-of-00048.safetensors5.29 GBcc9165793f1f879218c28a8d62067e077e10bb4bc2ec39848c2921065d1b102c
model-00028-of-00048.safetensors5.29 GBb1866b2cf26888baf7cd8473faa86e96db5643e12d149303be731a611b2d2f80
model-00029-of-00048.safetensors5.29 GBa42f85de65aed94ad6b155ec6b36f1732787490e7a98b85886980cbdba898f3c
model-00030-of-00048.safetensors5.29 GB9e83193d3613d2516ca4377c19539b29b0ecdb8c8dd529edb69654d193315c28
model-00031-of-00048.safetensors5.29 GB8d6951068638bbe1c8e3d3e2229d18c20653c8d6ba525d13dc33015acb73276a
model-00032-of-00048.safetensors5.29 GB6d546d1addd280c17cab5a13c031ba7742b0896e1d0a3ba637f65955378c68fa
model-00033-of-00048.safetensors5.29 GB51f5c84a8563d5e80219f2d1d6b0dbbf23fe290edb8ccdacfa90973b0695cbf5
model-00034-of-00048.safetensors5.29 GBb2f8018646ac92c309e11e293a98b602f5fea02bf4e2cc4976ee5e5d0958aa95
model-00035-of-00048.safetensors5.29 GB457f74b0e0bf6241ef3d8c8d697d1c9af0edf223fcaf249a2d26d488fdb33a59
model-00036-of-00048.safetensors5.29 GBe1c3106955a435115c35e624dbec62fba0a241f7d7e67bc41d2674817de4b794
model-00037-of-00048.safetensors5.29 GB0feb0b75848886c4536946cb32f2e028d1f02250f92378f5c5ccfe0cadf0254f
model-00038-of-00048.safetensors5.29 GB38cde377156a219250d74f30420e3ce0a7ba493c63c2651fc33e85598023a8d9
model-00039-of-00048.safetensors5.29 GBfad8eb0b34589d9940f974a207196b5cdc7a0a4ed585161e6949d21a70c6dbf4
model-00040-of-00048.safetensors5.29 GB95a577f8906204680aeff70df4dc841ca9ba91da782ee51d0284d2d82a9c83da
model-00041-of-00048.safetensors5.29 GB9eeadb29c11250f1b2f772acaa6cf6552108212e2c71780b6356f8315899f6ec
model-00042-of-00048.safetensors5.29 GB4fa9217acdf0980f9476931fd112820e11850a1cef52bcc1ccd0532c69c60f7f
model-00043-of-00048.safetensors5.29 GBeb48330917cc8cffed14ca45d7c1af196fe190577fb7487ac671c0132a7e910a
model-00044-of-00048.safetensors5.29 GB66f154fcc3312551b6336084257c0bf6873d9d861f36e45ced9c7fd4240cbc40
model-00045-of-00048.safetensors5.29 GB6099d5dcbfecec04aca466aee33d492d0790dc848c46cf25d1dff8812e4d0e5d
model-00046-of-00048.safetensors5.29 GB45580b9c418432b50f3e90e1a6fad5fd5173c058018e7d0a99373dec5ac8f7ea
model-00047-of-00048.safetensors5.29 GB9eb747d734c62f34e9321141982dcc1a8185abb0892bc52fd90717845945210f
model-00048-of-00048.safetensors1.52 GBd49493db6125d9053fb395712fc7f9d3a1f0840c60ef86e50c73d6dfc471f50d
model.safetensors.index.json234 KB3ba9bfef25bf7bc52c66ddb39554aefc54536e080a49e6ae14f99300f995d5e0
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
9704289308 pinned now2026-11-15 05:11 UTC60 files · 250 GB

Use it

$ fw get mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit
# manifest sha256 0b9310d97ab8… · 250 GB · 60 files
$ fw verify ./Qwen3-235B-A22B-Instruct-2507-8bit mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit
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-Instruct-2507-8bit.json --dir ./Qwen3-235B-A22B-Instruct-2507-8bit $ python3 fw.py verify ./Qwen3-235B-A22B-Instruct-2507-8bit ./mlx-community__Qwen3-235B-A22B-Instruct-2507-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit --revision 97042893088decff8468f7729c1076dcad2f251b --local-dir ./Qwen3-235B-A22B-Instruct-2507-8bit
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-Instruct-2507-8bit", revision="97042893088decff8468f7729c1076dcad2f251b") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit", revision="97042893088decff8468f7729c1076dcad2f251b", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit --revision 97042893088decff8468f7729c1076dcad2f251b

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
571fe26ed4b0791757f2d20b562f5a1e7ed2ff909163305dd0a0a7347916f477
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-Instruct-2507-8bitDate: 2026-11-15Commit: 9704289Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit
Pinned commit
97042893088decff8468f7729c1076dcad2f251b
Manifest
Qwen3-235B-A22B-Instruct-2507-8bit.json · .minisig
Manifest sha256
0b9310d97ab8830a03ee320299c1132e5a213d73597e6c339c91a2478580680f
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:11 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit.json.minisig $ minisign -Vm Qwen3-235B-A22B-Instruct-2507-8bit.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-Instruct-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-Instruct-2507-8bit
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-Instruct-2507-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit

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