models · qwen

Qwen2.5-3B-Instruct

Qwen2.5 3B instruction model. Suitable for edge/mobile deployment.

What this registry has checked

Hardened. We downloaded these weights and hashed them ourselves. The hash below is ours, not a publisher’s claim. It does not assert that the model is safe, accurate, or fit for any purpose. It says the bytes are the bytes.

Weight file SHA-256	3502aa56cf7abbb026b4f0457050dd31ee615387b6c9ca661bc234b18167e1eb
Method	self-download-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	qwen
Origin	China
Licence	Apache-2.0
Publisher’s own licence statement	other
Parameters	3,085,938,688 (3.09B)
Architecture	qwen2
Layers	36
Hidden size	2048
Attention	GQA (16 heads, 2 KV)
Native precision	BF16
Pulls recorded here	38,006
Downloads reported upstream	5,386,896

Elsewhere in the registry

All models → Browse with filters → What will run on my hardware? →

Registry record as of 2026-06-11. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.