models · qwen

Qwen3 VL 8B Instruct

Qwen3 VL 8B Instruct — catalogued from third-party evaluation data; no weights held by Sovereign Frontier.

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	China
Licence	Apache-2.0
Parameters	8,767,123,696 (8.77B)
Context window	262,144 tokens
Modality	text+image->text
Native precision	BF16
Downloads reported upstream	19,149,628

Reported scores

MMLU-Pro	68.6
GPQA Diamond	42.7
AIME 2025	27.3
LiveCodeBench	33.2
IFBench	32.3
Humanity's Last Exam	2.7

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
Radeon AI PRO R9700 ×3 devices	llama.cpp	Q8_0	58.8 tok/s @ 786	candidate	localmaxxing

From local-ai-registry (MIT), commit 124959d: 1 run across 1 machine, 0 validated — model revision and runtime pinned, launch accepted — and 1 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 2026-09-26. 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.