models · qwen

Qwen3.8-27B

image-text-to-text model harvested from Hugging Face (trending). Catalogued at Quarantine — unverified, pending attestation.

Compare Verify

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	apache-2.0
Parameters	27,781,427,952 (27.8B)
Context window	262,144 tokens
Modality	text+image+video->text
Native precision	BF16
Pulls recorded here	91,917
Downloads reported upstream	7,703,400

Reported scores

GPQA Diamond	90.5
Humanity's Last Exam	33.9

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

Measured on real hardware

None of these runs are ours. Each figure is the reporter’s, linked to their own evidence, under their own trust label. The number shown is single-stream decode — one user, concurrency 1 — because aggregate throughput across many users is a different quantity and reads as far faster than anyone will see.

Reported to local-ai-registry

Hardware	Engine	Build measured	Decode, 1 stream	Label	Reported by
GeForce RTX 3090 ×4 devices	sglang	AWQ INT4 W4A16	137 tok/s @ 8,744	validated	0xsero
NVIDIA RTX PRO 4500 Blackwell	TabbyAPI (ExLlamaV3)	EXL3 SC 4.00bpw H5	117 tok/s @ 32,768	validated	0xsero
GeForce RTX 5090	llama.cpp	UD-Q4_K_XL	116 tok/s @ 2,048	candidate	localmaxxing
GeForce RTX 5090	llama.cpp	Q4_K_S	102 tok/s @ 2,048	candidate	localmaxxing
GeForce RTX 5090	llama.cpp	Q6_K	97.7 tok/s @ 2,048	candidate	localmaxxing
Radeon RX 7900 XTX	llama.cpp	Q4_K_XL	90.7 tok/s @ 32,768	candidate	localmaxxing
Ryzen AI Max+ 395	llama.cpp	IU4	90.1 tok/s @ 32,768	candidate	localmaxxing
GeForce RTX 5090	ollama	Q4_K_M	82.0 tok/s @ 16,384	candidate	0xsero
GeForce RTX 3080	llama.cpp	IQ2_XXS	74.1 tok/s @ 16,384	candidate	localmaxxing
GeForce RTX 3090 ×2 devices	bunn-llama	Q4_K_XL	73.0 tok/s @ 2,048	candidate	localmaxxing

From local-ai-registry (MIT), commit 124959d: 251 runs across 45 machines, 49 validated — model revision and runtime pinned, launch accepted — and 202 candidate, their label for useful evidence without a reproducible-launch promise. 149 more not listed. 14 report figures that contradict each other — prefill below decode, which parallel prefill essentially never is — and are left to the source rather than ranked here.

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.