models · qwen

Qwen3-1.7B

Smallest Qwen3 model. On-device inference capable, strong for size.

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	71ce940ab74a72abcab06f46d4a6deb379644f659b5cd1384c40cf86372714ee
Method	self-download-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	qwen
Origin	China
Licence	Apache-2.0
Parameters	2,031,739,904 (2.03B)
Architecture	qwen3
Layers	28
Hidden size	2048
Attention	GQA (16 heads, 8 KV)
Native precision	BF16
Pulls recorded here	48,015
Downloads reported upstream	3,585,353

Reported scores

MMLU-Pro	41.1
GPQA Diamond	28.3
AIME 2025	7.3
MATH-500	71.7
LiveCodeBench	12.6
IFBench	21.1
Humanity's Last Exam	5.3

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

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.