← Back to community benchmarks

gemma-4-e4b-it

M2 (10c) · 16 GB · 4bit · 2026-07-24

Performance

64k

tokens

246.9

PP tok/s

13.9

TG tok/s

265484

TTFT (ms)

6.4

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.5.3

macOS macOS 15.7.7

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	309.3	26.5	4.5 GB	view
16k	302.5	23.4	4.9 GB	view
64k	246.9	13.9	6.4 GB	current