← Back to community benchmarks

gemma-4-e2b-it

M1 Pro (14c) · 32 GB · 4bit · 2026-05-08

Performance

64k

tokens

1,032

PP tok/s

34.0

TG tok/s

63500

TTFT (ms)

5.3

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 32 GB

GPU Cores 14

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	1,264	44.6	4.5 GB	view
64k	1,032	34.0	5.3 GB	current
128k	717.5	22.9	6.7 GB	view