Qwen/Qwen3-4B
Qwen/Qwen3-4B is an open-weights language model for text generation under the apache-2.0 license (8.0 GB), added to Hugging Bay Jun 29, 2026. Hosted open-weights model — 9 files carry published SHA-256 checksums you can re-hash. 9 Hugging Bay hosted files.
- Task
- text generation
- Size
- 8.0 GB
- Recommended file
- 8.0 GB (3 files)
- Parameters
- 4B
- Files
- 9 hosted of 9 listed
- Added to Hugging Bay
- Updated at source
Download this program
Your file is ready.
Qwen3-4B — 1 file — published by Qwen
model-00002-of-00003.safetensors · 4.0 GB
Download the file
Make sure it arrived whole — checking a 4.0 GB file can take a few minutes
Think of the fingerprint below as the file's ID photo: a string unique to its exact bytes.
On a Mac, the Terminal line below prints this file's SHA-256 fingerprint; it already contains your file's name and assumes the file is in your Downloads folder.
After the download finishes, paste it into Terminal and press Return.
Terminal shasum -a 256 ~/Downloads/model-00002-of-00003.safetensors
On Windows, the PowerShell line below prints this file's SHA-256 fingerprint; it already contains your file's name and assumes the file is in your Downloads folder.
After the download finishes, paste it into PowerShell and press Enter.
PowerShell Get-FileHash -Algorithm SHA256 "$HOME\Downloads\model-00002-of-00003.safetensors"
From Command Prompt instead: certutil -hashfile "%USERPROFILE%\Downloads\model-00002-of-00003.safetensors" SHA256
PowerShell prints the same SHA-256 fingerprint in capital letters.
On Linux, the terminal line below prints this file's SHA-256 fingerprint; it already contains your file's name and assumes the file is in your Downloads folder.
After the download finishes, paste it into a terminal and press Enter.
Terminal sha256sum ~/Downloads/model-00002-of-00003.safetensors
If the string it prints matches this one, you're holding exactly what we published:
6cd0...1ca5
File fingerprint (for experts)
6cd087b316306a68c562436b5492edbcf6e16c6dba3a1308279caa5a58e21ca5
This check proves the file arrived unchanged — not that the program is safe.
What we've checked:
- License — passed (apache-2.0)
- Files hosted — 9 of 9 from the repository
Other files (for experts)
CHAT
A chat model you use like ChatGPT — but here it’s a set of files: download them and load them with a Python library such as Hugging Face transformers on a computer.
You don’t need to know what a “model” is. This is the one for chatting.
Not sure what you’d use it for? Try one question — that’s the whole test. Try: “Explain photosynthesis like I’m five.”
About this download
Not a fact-checker. Not a search engine. It can be confidently wrong.
FAQ
What is Qwen/Qwen3-4B?
Qwen/Qwen3-4B is an open-weights language model for text generation published by Qwen, added to Hugging Bay Jun 29, 2026. Model from Hugging Face: Qwen/Qwen3-4B
What license does Qwen/Qwen3-4B use, and 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 Qwen/Qwen3-4B?
Qwen/Qwen3-4B has 4B parameters. The total download is 8.0 GB; the recommended download, a 3-file weight set, is 8.0 GB.
Where can I download Qwen/Qwen3-4B?
Hugging Bay hosts 9 of 9 files for this model, each with a published SHA-256 checksum. Total size: 8.0 GB. The original release is at https://huggingface.co/Qwen/Qwen3-4B.
Has Qwen/Qwen3-4B been scanned for unsafe files?
Source scan status: passed. A scan checks the files for known-bad signatures — it does not mean the model is safe. 9 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-qwen-qwen3-4b/safety on Hugging Bay.
Will Qwen/Qwen3-4B 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. Start the check at /find on Hugging Bay — we won't guess from a generic GPU.
About this artifact
External Hugging Face catalog record for Qwen/Qwen3-4B. Popularity signal at import: 12,641,936 downloads and 643 likes. Files are listed for discovery and verification context, but this Hugging Bay pilot has not mirrored or rescanned the remote blobs. Use the upstream Hugging Face links for download until an explicit mirror job is approved.
Hosted file inventory
Hosted file — the exact bytes are complete.. The immutable selected representation is byte-complete; runtime compatibility is not established.
- Hosted files
- 9 of 9
- 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
- complete-bytes
- Evidence timestamp
- 2026-08-17T18:47:05.123Z
- Selected representation
- rep-16363654b020189b29e34848f10e4b191ba04e193c0bf642a14f801e482ddfd8
- Complete bytes
- yes
- Complete kit
- no
- Byte-integrity check
- not established — the hosted bytes are not yet matched to a signed upstream manifest
- Run ready
- not established
- Files
- View file metadata
Bay Run
Try It Now unavailable
Bay Run does not publish a serving contract for this exact artifact and Hugging Bay will not invent one.
Mint a Pin unavailable
Bay Run does not publish a serving contract for this exact artifact and Hugging Bay will not invent one.
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.
Download exact selected bytes
- License: pass - apache-2.0
- Provenance: pass - Qwen/Qwen3-4B
- Scan: pass - passed
- Hosted files: pass - 9/9 repository files hosted
- Byte manifest integrity: pass - selected representation is complete-bytes; per-file SHA-256 published (cryptographic signing pending)
Machine-readable card
Open interactive artifact page
Evidence details
- Demand
- 16M upstream downloads
- Trust
- Unknown
- Download completeness
- Hosted file — the exact bytes are complete.
- Run fit
- Exact selected bytes complete; runtime not established
- Scan status
- passed
- Executable state
- complete-bytes
- Evidence timestamp
- 2026-08-17T18:47:05.123Z
- Declared license
- apache-2.0
- Pipeline
- text-generation
- Library
- transformers
- Task categories
- text-generation