CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.5-122B-A10B-6bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-122B-A10B-6bit

Date: 2026-11-15Commit: 1a4943cSigned: 2DC28CC7B26A283B ✓

Image text to text model with 122.6B parameters. Safetensors weights, 100 GB in all. Published by mlx-community under Apache-2.0.

122.6B params100GBQwen3.5-122B-A10B-6bitsafetensorspermissive
FactsParams122.6BSize100 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3.5-122B-A10B-6bit
# manifest sha256 d76ac1d32641… · 100 GB · 32 files
$ fw verify ./Qwen3.5-122B-A10B-6bit mlx-community/Qwen3.5-122B-A10B-6bit
From sourceHosted (signed)mlx-community/Qwen3.5-122B-A10B-6bitLast check: 2026-11-15 03:43 UTC
Get help

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

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
100 GB
Weights
100 GB (safetensors)
Parameters
122.6B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
32, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

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 03:43 UTCpassed

Model card

From the publisher at commit 1a4943c. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3.5-122B-A10B-6bit#

This model was converted to MLX format from Qwen/Qwen3.5-122B-A10B using mlx-vlm version 0.3.12. Refer to the original model card for more details on the model.

Use with mlx#

pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/Qwen3.5-122B-A10B-6bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

32 files · 100 GBWeights 100 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 32 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md666 B032363b7123dd9f9303d06d61889d68985f22e939961090b312b2ee9f2c48fce
chat_template.jinja7.76 KBa4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715
config.json4.06 KBa80c5993760437590090778eb060ed0915acf75df7de77a43a8f7dc878f02291
generation_config.json244 B303aba891d66ab63908a7b3cc9163bcb835fdf8b9f6301c73216f3f1eb3992dd
model-00001-of-00020.safetensors4.95 GB6f338cc025addc19d90f5e0b0fc1d623eed503505b16795405b49e503b8e422c
model-00002-of-00020.safetensors4.81 GB612d7a74a02ec47a9d659ece97bac980b6e003d581fc68ecad1547c1116ab042
model-00003-of-00020.safetensors5.34 GBbad48182b0380906764788a3be1e9a1fc14e7be5523c4cb1ea9a9ee1848e0063
model-00004-of-00020.safetensors4.86 GBcb2da72d4972fd635d20c267294c29b21ac561bfb67e1eeac242b2b8de9fcd46
model-00005-of-00020.safetensors5.36 GB91202707909a30b33ffaaeeb871cfd70f82cc2cb5b8186221ecf45b942434c38
model-00006-of-00020.safetensors4.85 GB94245268ad16eeaa3b0404cd6badc4d394234e7f92a79e18f6af9d1af47f3481
model-00007-of-00020.safetensors5.36 GBaf6ca6b4f77b24db68e6eecae07f6cc6fc0fa427431ad7d173959f078dde8996
model-00008-of-00020.safetensors4.84 GB750af2856c0be894b4f81fe489de5273bcdab22af45206a104daa993189673e4
model-00009-of-00020.safetensors5.34 GB9645e36959c4f26b48bdc25cb3c24def60c17a389737d3c946c080bc495bf2eb
model-00010-of-00020.safetensors4.86 GB8b19eaade67f125e32844e8c699b5b4bb09da6885aae556cb776177a5f7fd4e9
model-00011-of-00020.safetensors5.34 GB8a90e62c215969bd2d0f5d2d356555b043f87a4fe35b3f0af5184aedfbb37788
model-00012-of-00020.safetensors4.86 GB8ce68a8bcd4479cdaa5ef25adaa73079fa9770a63ece131752dd31de22b75661
model-00013-of-00020.safetensors5.36 GBaeb0ed569611bf03972816c6af2f6db4cf94c2605c6c0f7cc39ed14f1d0aa6f4
model-00014-of-00020.safetensors4.85 GB2c11a735523c0ccb1f4ac10e6f2df68924854662ca4c66c27e3d536bddda90e9
model-00015-of-00020.safetensors5.36 GBb4e4826d2227ca0f63e5a01210c4b026f672f78561a2d7538291d0e3f4868a72
model-00016-of-00020.safetensors4.84 GBf0ba9f4a930743d024098c3fcbe85f35a4ae76bcc4162cdfc3af2c75540ce196
model-00017-of-00020.safetensors5.34 GBefcf8fd865df8bdf6d001a8530ca21f0378db815ec38f9e7d812da0118045e20
model-00018-of-00020.safetensors4.86 GB9afac9fdd18224c164c2a7115ec0365abf901533ee7dec6a159c5a028b59933f
model-00019-of-00020.safetensors5.34 GBdfd78d3e578e66ae8e6c2dc73d9bb4e309a08efd085e9f481d51c06756b0913e
model-00020-of-00020.safetensors3.37 GB09aeaf8713904cf95ae83601e9eded0f2ccd38af52eb7b91b845cbdb3fdee4e0
model.safetensors.index.json253 KBc457b54261c516e48739ec52a387ebef142ae03049e7328bdf9a1f735c5d385b
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
processor_config.json1.30 KB14932921ca485d458a04dafd8069fbb0a4505622a48208d19ed247115801385b
tokenizer.json20.0 MB87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
tokenizer_config.json1.14 KBe98f1901ac6f0adff67b1d540bfa0c36ac1a0cf59eb72ed78146ef89aafa1182
video_preprocessor_config.json385 B7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1a4943cb97 pinned now2026-11-15 03:43 UTC32 files · 100 GB

Use it

$ fw get mlx-community/Qwen3.5-122B-A10B-6bit
# manifest sha256 d76ac1d32641… · 100 GB · 32 files
$ fw verify ./Qwen3.5-122B-A10B-6bit mlx-community/Qwen3.5-122B-A10B-6bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-122B-A10B-6bit.json --dir ./Qwen3.5-122B-A10B-6bit $ python3 fw.py verify ./Qwen3.5-122B-A10B-6bit ./mlx-community__Qwen3.5-122B-A10B-6bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.5-122B-A10B-6bit --revision 1a4943cb97f1d3ec701c3c98c7b067f71888dd71 --local-dir ./Qwen3.5-122B-A10B-6bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/Qwen3.5-122B-A10B-6bit", revision="1a4943cb97f1d3ec701c3c98c7b067f71888dd71") model = AutoModelForImageTextToText.from_pretrained("mlx-community/Qwen3.5-122B-A10B-6bit", revision="1a4943cb97f1d3ec701c3c98c7b067f71888dd71", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3.5-122B-A10B-6bit --revision 1a4943cb97f1d3ec701c3c98c7b067f71888dd71

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
032363b7123dd9f9303d06d61889d68985f22e939961090b312b2ee9f2c48fce
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: Qwen3.5-122B-A10B-6bitDate: 2026-11-15Commit: 1a4943cSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3.5-122B-A10B-6bit
Pinned commit
1a4943cb97f1d3ec701c3c98c7b067f71888dd71
Manifest
Qwen3.5-122B-A10B-6bit.json · .minisig
Manifest sha256
d76ac1d3264113d8cea6d7a6ea7b94abaf45579015dca2dbd24699cd5f777d9b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:43 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-122B-A10B-6bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-122B-A10B-6bit.json.minisig $ minisign -Vm Qwen3.5-122B-A10B-6bit.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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.5-122B-A10B-6bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.5-122B-A10B-6bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3.5-122B-A10B-6bit

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