Qwen/Qwen3-4B-Instruct-2507 files
Qwen/Qwen3-4B-Instruct-2507 file list, hosted download status, recorded SHA-256 values, manifest links, and source provenance for 9 hosted files out of 9 indexed files.
- Task
- text generation
- Size
- 8.1 GB
- Recommended file
- 8.0 GB (3 files)
- Parameters
- 4B
- Files
- 9 hosted of 9 listed
- Download
- Download here (9 hosted files)
- Added to Hugging Bay
- Updated at source
Download this program
Weights · 3 files
Other files (for experts)
- config.json · 727 bytes
- generation_config.json · 238 bytes
- merges.txt · 1.7 MB
- model-00002-of-00003.safetensors · 4.0 GB
- model-00003-of-00003.safetensors · 100 MB
- model.safetensors.index.json · 33 KB
- tokenizer_config.json · 9 KB
- vocab.json · 2.8 MB
CHAT
A chat model — 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 this model?
Qwen/Qwen3-4B-Instruct-2507 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-Instruct-2507
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/Qwen3-4B-Instruct-2507 has 4B parameters. The total download is 8.1 GB; the recommended download, a 3-file weight set, is 8.0 GB.
What can I download here?
Hugging Bay hosts 9 of 9 files for this model, each with a published SHA-256 checksum. Total size: 8.1 GB. The original release is at https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507.
File checks and computer fit
File pattern scans
Automated file-pattern scans flagged nothing — not a safety guarantee. 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-instruct-2507/safety on Hugging Bay.
Will Qwen/Qwen3-4B-Instruct-2507 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.
Files and download status
9 of 9 indexed files are hosted here, with SHA-256 hashes, manifests, and resumable downloads. Check the Run tab for complete-kit status.
- config.json - 727 B - mirrored-upstream - risk low
- generation_config.json - 238 B - mirrored-upstream - risk low
- merges.txt - 1.6 MB - mirrored-upstream - risk low
- model-00001-of-00003.safetensors - 3.7 GB - mirrored-upstream - risk low
- model-00002-of-00003.safetensors - 3.7 GB - mirrored-upstream - risk low
- model-00003-of-00003.safetensors - 95 MB - mirrored-upstream - risk low
- model.safetensors.index.json - 32 KB - mirrored-upstream - risk low
- tokenizer_config.json - 9.2 KB - mirrored-upstream - risk low
- vocab.json - 2.6 MB - mirrored-upstream - risk low
Files API Hosted downloads API Open interactive files tab
Evidence details
- Demand
- 5.4M 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
- 2026-08-18T01:39:46.219Z
- Declared license
- apache-2.0
- Pipeline
- text-generation
- Library
- transformers
- Task categories
- text-generation