← Back to community benchmarks

gemma-4-26B-A4B-it-oQ5-5.7b

M2 Pro (19c) · 32 GB · 5bit · 2026-05-15

Performance

1k

tokens

495.4

PP tok/s

34.9

TG tok/s

2067

TTFT (ms)

17.4

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 32 GB

GPU Cores 19

Software

oMLX v0.3.9.dev2

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	495.4	34.9	17.4 GB	current
4k	550.2	34.7	17.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	34.9	1.00×
2×	50.0	1.43×
4×	56.5	1.62×