models · google

Gemma 3n E4B

Gemma 3 nano-style E4B model for on-device inference — the smallest Gemma 3 variant.

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	dda38b407e8b9db97c03399db6a4479ca09f4f8b911df58717489585579b6856
Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	google
Origin	United States
Licence	Gemma-TOS
Publisher’s own licence statement	gemma
Parameters	7,849,978,192 (7.85B)
Native precision	BF16
Pulls recorded here	37,006
Downloads reported upstream	1,743

Reported scores

MMLU-Pro	48.8
GPQA Diamond	29.6
AIME 2025	14.3
MATH-500	77.1
LiveCodeBench	14.6
IFBench	27.9
Humanity's Last Exam	4.5

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Elsewhere in the registry

All models → Browse with filters → What will run on my hardware? →

Registry record as of 2026-07-25. 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.