models · Qwen

Qwen2.5-VL-72B-Instruct

Catalogued from llm-stats Open LLM Leaderboard at Quarantine — unverified, pending attestation.

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.

Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	Qwen
Origin	Recorded as a covered nation under 10 U.S.C. § 4872(f) — the PRC, Russia, Iran or North Korea. The registry did not record which.
Licence	unknown
Publisher’s own licence statement	other
Parameters	73,410,777,344 (73.4B)
Context window	128,000 tokens
Modality	text+image->text
Architecture	qwen2_5_vl
Layers	80
Hidden size	8192
Attention	GQA (64 heads, 8 KV)
Native precision	BF16
Pulls recorded here	6
Downloads reported upstream	114,282

Elsewhere in the registry

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

Registry record as of 2026-09-01. 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.