models · tencent

Hy3

text-generation 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	tencent
Origin	China
Licence	apache-2.0
Parameters	298,786,155,776 (298.8B)
Context window	262,144 tokens
Modality	text->text
Architecture	hy_v3
Layers	80
Hidden size	4096
Attention	GQA (64 heads, 8 KV)
Native precision	BF16
Pulls recorded here	5,578
Downloads reported upstream	13,103

Reported scores

GPQA Diamond	89.7
Humanity's Last Exam	33.5

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 ×4 devices	llama.cpp	IQ1_M	87.1 tok/s @ 131,072	candidate	localmaxxing

From local-ai-registry (MIT), commit 124959d: 3 runs across 3 machines, 0 validated — model revision and runtime pinned, launch accepted — and 3 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 2026-09-01. 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.