models · google

gemma-4-26B-A4B-it

Catalogued from local.ai local-inference benchmark index at Quarantine — unverified, pending attestation.

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	google
Origin	United States
Licence	Apache-2.0
Parameters	25,805,936,206 (25.8B)
Context window	262,144 tokens
Modality	text+image+video->text
Native precision	BF16
Downloads reported upstream	8,818,645

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	Q3_K_M	256 tok/s @ 2,048	candidate	localmaxxing
Intel Arc Pro B70	llama.cpp	Q8_K_XL	125 tok/s @ 32,768	candidate	localmaxxing
Radeon PRO W7800	llama.cpp	Q4_K_S	117 tok/s @ 8,192	validated	0xsero
Intel Arc Pro B70	llama.cpp	UD-Q8_K_XL	115 tok/s @ 32,768	candidate	localmaxxing
Radeon PRO W7800	llama.cpp	UD-Q4_K_XL	113 tok/s @ 8,192	validated	0xsero
GeForce RTX 5060 Ti	llama.cpp	Q3_K_M	106 tok/s @ 2,048	candidate	localmaxxing
Apple M5 Max 128GB	mlx	MLX 4bit	102 tok/s @ 8,256	candidate	exo-postgres
GeForce RTX 5060 Ti	llama.cpp	Q3_K_XL	101 tok/s @ 2,048	candidate	localmaxxing
Radeon AI PRO R9700	llama.cpp	Q4_K_XL	98.0 tok/s @ 2,048	candidate	localmaxxing
Apple M4 Max 128GB	mlx	MLX 4bit	92.3 tok/s @ 8,256	candidate	exo-postgres

From local-ai-registry (MIT), commit 124959d: 58 runs across 23 machines, 8 validated — model revision and runtime pinned, launch accepted — and 50 candidate, their label for useful evidence without a reproducible-launch promise. 31 more not listed.

Measured by local.ai

Hardware	Build measured	Decode @ 8K	Memory @ 8K	Decode mode
NVIDIA RTX PRO 6000 Blackwell 96GB	AWQ-4bit	202 tok/s	90.4 GB	ordinary
NVIDIA GeForce RTX 5090 32GB	AWQ-4bit	192 tok/s	29.3 GB	ordinary
NVIDIA RTX PRO 6000 Blackwell 96GB	fp8	165 tok/s	90.7 GB	ordinary
NVIDIA RTX 6000 Ada 48GB	AWQ-4bit	146 tok/s	44.4 GB	ordinary
NVIDIA GeForce RTX 4090 24GB	AWQ-4bit	132 tok/s	21.8 GB	ordinary
NVIDIA RTX 6000 Ada 48GB	fp8	119 tok/s	44.3 GB	ordinary
MacBook Pro M5 Max 128GB · 40-core GPU	4bit	103 tok/s	16.6 GB	ordinary
MacBook Pro M4 Max 128GB · 40-core GPU	4bit	92.5 tok/s	28.5 GB	ordinary

Measured by local.ai, not by us: 67 runs, 59 more not listed. Each names its engine pinned by image digest and the exact serve command, in the full record.

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.