← Back to community benchmarks

gemma-4-26B-A4B-it

M2 Pro (19c) · 32 GB · 4bit · 2026-04-29

Performance

4k

tokens

320.2

PP tok/s

43.5

TG tok/s

12791

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 32 GB

GPU Cores 19

Software

oMLX v0.3.8rc1

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	297.5	45.0	14.3 GB	view
4k	320.2	43.5	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	45.0	1.00×
2×	57.4	1.28×
4×	63.4	1.41×
8×	68.8	1.53×