models · qwen

Qwen3.5-27B

Qwen3.5 dense 27B instruct. 262K context. Strong at coding and math; competitive with prior 70B-class models.

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	76e97b66c81294a6357dbe2cfb53e7a3674b0b6d78bf9368f07857698346f44b
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	262K
Modality	text+image+video->text
Native precision	BF16
Pulls recorded here	390,015
Downloads reported upstream	2,005,300

Reported scores

GPQA Diamond	85.8
IFBench	75.6
Humanity's Last Exam	23.9

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 4090	llama.cpp	Q4_K_M	46.7 tok/s @ 2,048	candidate	localmaxxing
GeForce RTX 4090	llama.cpp	Q4_0	44.0 tok/s @ 2,048	candidate	localmaxxing
GeForce RTX 3090	llama.cpp	Q4_K_M	40.9 tok/s @ 2,048	candidate	localmaxxing
GeForce RTX 3090	llama.cpp	Q4_0	38.4 tok/s @ 2,048	candidate	localmaxxing
Radeon AI PRO R9700	llama.cpp	Q4_K_XL	29.4 tok/s @ 2,048	candidate	localmaxxing
Radeon AI PRO R9700	llama.cpp	Q4_K_XL	26.7 tok/s @ 2,048	candidate	localmaxxing
Intel Arc Pro B70	llama.cpp	Q4_K_XL	18.0 tok/s @ 8,192	candidate	localmaxxing
Ryzen AI Max+ 395	llama.cpp	Q4_K_M	13.0 tok/s @ 32,768	candidate	localmaxxing
Ryzen AI Max+ 395	llama.cpp	Q5_K_M	11.3 tok/s @ 32,768	candidate	localmaxxing
Ryzen AI Max+ 395	llama.cpp	Q6_K	9.9 tok/s @ 32,768	candidate	localmaxxing

From local-ai-registry (MIT), commit 124959d: 26 runs across 9 machines, 0 validated — model revision and runtime pinned, launch accepted — and 26 candidate, their label for useful evidence without a reproducible-launch promise. 6 more not listed.

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.