models · qwen

Qwen2.5-1.5B-Instruct

Compact Qwen2.5 1.5B for on-device tasks.

Compare Verify

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-256432f51c1994536ddac344cfbd57d74ac9294588278c2c9aaebfaeb9add6da354
Methodself-download-sha256

What is recorded

Publisherqwen
OriginChina
LicenceApache-2.0
Parameters1,543,714,304 (1.54B)
Architectureqwen2
Layers28
Hidden size1536
AttentionGQA (12 heads, 2 KV)
Native precisionBF16
Pulls recorded here27,007
Downloads reported upstream7,132,599

Elsewhere in the registry

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.