models · lmsys

Vicuna-33B-v1.3

Vicuna 33B — LMSYS fine-tune of LLaMA for high-quality multi-turn conversations.

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.

Weight file SHA-256	4480e5141c7082f9bb8ff99c442678a5c6283d60c8a4e3abb6c2fbfd603c88f3
Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	lmsys
Origin	United States
Licence	Llama-2
Architecture	llama
Layers	60
Hidden size	6656
Attention	MHA (52 heads, 52 KV)
Native precision	float16
Pulls recorded here	31,006

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.