← Back to community benchmarks

gemma-4-e2b

M2 Pro (19c) · 32 GB · 4bit · 2026-04-05

Performance

4k

tokens

1,614

PP tok/s

76.0

TG tok/s

2538

TTFT (ms)

3.4

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 32 GB

GPU Cores 19

Software

oMLX v0.3.4

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,073	82.3	3.2 GB	view
4k	1,614	76.0	3.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	82.3	1.00×
2×	99.6	1.21×
4×	109.0	1.32×