models · qwen

Qwen3-8B

Qwen3 8B dense instruct model. Competitive with much larger models on reasoning tasks. Ideal for edge and resource-constrained deployments.

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.

Weight file SHA-256	3527d355ea6aed6c2be0210e8fc321a818f8e616c11786884be4a6a128589a9a
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	8,190,735,360 (8.19B)
Context window	128K
Modality	text->text
Architecture	qwen3
Layers	36
Hidden size	4096
Attention	GQA (32 heads, 8 KV)
Native precision	BF16
Pulls recorded here	930,044
Downloads reported upstream	12,717,110

Reported scores

MMLU-Pro	64.3
GPQA Diamond	45.2
AIME 2025	24.3
MATH-500	82.8
LiveCodeBench	20.2
IFBench	28.6
Humanity's Last Exam	1.9

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 5090	llama.cpp	Q4_K_M	227 tok/s @ 8,192	candidate	localmaxxing
GeForce RTX 3090 Ti	llama.cpp	Q4_K_M	133 tok/s @ 8,192	candidate	localmaxxing
Measured outside 2K–32K context — decode speed depends heavily on context, so these are not comparable with the rows above
GeForce RTX 3060 Ti	llama.cpp	Q4_K_M	71.7 tok/s @ 512	candidate	localmaxxing
GeForce RTX 3060	llama.cpp	Q4_K_M	62.5 tok/s @ 512	candidate	localmaxxing

From local-ai-registry (MIT), commit 124959d: 4 runs across 4 machines, 0 validated — model revision and runtime pinned, launch accepted — and 4 candidate, their label for useful evidence without a reproducible-launch promise.

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.