models · zai-org

GLM-5.3

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	zai-org
Origin	China
Licence	other
Parameters	753,329,940,480 (753.3B)
Context window	1,048,576 tokens
Modality	text->text
Architecture	glm_moe_dsa
Layers	78
Hidden size	6144
Attention	MLA (64 heads, 64 KV)
Native precision	F8_E4M3

Reported scores

GPQA Diamond	91.7
Humanity's Last Exam	42.3

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
RTX PRO 6000 Blackwell ×4 devices	vllm	EXL3 Trellis TR3 3.0 bpw	61.2 tok/s @ 78	candidate	0xsero

From local-ai-registry (MIT), commit 124959d: 3 runs across 1 machine, 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 2026-09-26. 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.