Skip to main content
The Hugging BayGet a model

AI models that run on this device.

Two small chat models run in a computer’s browser here; every other model is a file you download.

Qwen/Qwen3.6-35B-A3B

Qwen/Qwen3.6-35B-A3B is a vision model for vision-language chat under the apache-2.0 license (71.9 GB), added to Hugging Bay Jun 29, 2026. AI model cataloged from external huggingface metadata. Scan: passed.

Task
vision-language chat
Size
71.9 GB
Recommended file
54.1 GB (20 files)
Parameters
35B (3B active)
Files
0 hosted of 25 listed
Download
Downloadable files: 0 confirmed
Added to Hugging Bay
Updated at source

Download this program

Files withheld — not faked.

Other files (for experts)
  • .gitattributes · 2 KB
  • LICENSE · 11 KB
  • README.md · 65 KB
  • chat_template.jinja · 8 KB
  • configuration.json · 58 bytes
  • model-00002-of-00026.safetensors · 1.3 GB
  • model-00003-of-00026.safetensors · 3.4 GB
  • model-00004-of-00026.safetensors · 3.4 GB
  • model-00005-of-00026.safetensors · 3.4 GB
  • model-00006-of-00026.safetensors · 4.0 GB
  • model-00007-of-00026.safetensors · 1.1 GB
  • model-00008-of-00026.safetensors · 3.9 GB
  • model-00009-of-00026.safetensors · 1.1 GB
  • model-00010-of-00026.safetensors · 3.9 GB
  • model-00011-of-00026.safetensors · 1.1 GB
  • model-00012-of-00026.safetensors · 3.4 GB
  • model-00013-of-00026.safetensors · 1.6 GB
  • model-00014-of-00026.safetensors · 3.4 GB
  • model-00015-of-00026.safetensors · 1.6 GB
  • model-00016-of-00026.safetensors · 3.9 GB
  • model-00017-of-00026.safetensors · 1.1 GB
  • model-00018-of-00026.safetensors · 3.9 GB
  • model-00019-of-00026.safetensors · 1.1 GB
  • model-00020-of-00026.safetensors · 3.4 GB

FAQ

What is this model?

Qwen/Qwen3.6-35B-A3B is a vision model for vision-language chat published by Qwen, added to Hugging Bay Jun 29, 2026. Model from Hugging Face for image text to text: Qwen/Qwen3.6-35B-A3B · transformers

Can I use it commercially?

It is released under the apache-2.0 license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

How big is it?

Qwen/Qwen3.6-35B-A3B has 35B parameters (3B active per token). The full upstream repository is 71.9 GB; the recommended download, a 20-file weight set, is 54.1 GB.

What can I download here?

This model is listed, but we haven't confirmed its download files, so we won't offer a download button we can't stand behind. The record lists 25 files.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing — not a safety guarantee. The machine-readable verdict is at /api/artifacts/hf-model-qwen-qwen3-6-35b-a3b/safety on Hugging Bay.

Will Qwen/Qwen3.6-35B-A3B run on my computer?

We can’t check the fit — we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it — you can still download; fit isn’t checked.

About this artifact

External Hugging Face catalog record for Qwen/Qwen3.6-35B-A3B. Task: image text to text. Library: transformers. Files we host go through mirror review, a safety scan, and get a published SHA-256 before they're listed. Signing is not live yet.

Hosted file inventory

Hosted files
0 of 25
Reviewed peer-assisted fallbacks
0
Trust bundle
Trust-bundle JSON
Review summary
Review-summary JSON
Distribution
Reviewed peer-fallback JSON

Run status

Detailed evidence for the selected file set

This detail applies to the selected file set, not every file in the repository.

Executable state
unknown
Evidence timestamp
unknown
Selected representation
unknown
Complete bytes
unknown
Complete kit
unknown
Byte-integrity check
unknown
Run ready
unknown
Files
View file metadata

Bay Run

Bay Run pins; Try It Now unavailable

This artifact has no reviewed Hugging Bay-hosted file evidence. Request a reviewed mirror before trying Bay Run.

Mint a Pin unavailable

This artifact has no reviewed Hugging Bay-hosted file evidence. Request a reviewed mirror before creating a Bay Run Pin.

Guard before generate

Add Bay Run's provider-neutral coprocessor to your own generation pipeline. It checks decision.action before your generator runs.

npm install @huggingbay/coprocessor · Install @huggingbay/coprocessor

This handoff wraps your caller-owned generator. It does not run this catalog artifact, make it a Bay Run Pin, or change its serving or verification state.

Request a complete representation

  • License: pass - apache-2.0
  • Provenance: pass - Qwen/Qwen3.6-35B-A3B
  • Scan: pass - passed
  • Hosted files: warn - external metadata only
  • Byte manifest integrity: warn - not final yet

Machine-readable card

Open interactive artifact page

Evidence details

Demand
5.7M upstream downloads
Trust
Unknown
Run fit
Unknown: canonical-snapshot-missing
Scan status
passed
Executable state
unknown
Evidence timestamp
unknown
Declared license
apache-2.0
Pipeline
image-text-to-text
Library
transformers
Task categories
image-text-to-text
File hints
16 upstream file samples