← Back to community benchmarks

gemma-4-E2B-it-oQ8

M2 Max (38c) · 96 GB · 8bit · 2026-06-04

Performance

32k

tokens

4,192

PP tok/s

64.5

TG tok/s

7817

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.4.1

macOS macOS 15.7.5

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	4,979	76.1	6.3 GB	view
16k	4,901	67.9	6.4 GB	view
32k	4,192	64.5	6.7 GB	current
64k	3,257	54.4	7.4 GB	view