← Back to community benchmarks

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

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

Performance

4k

tokens

550.2

PP tok/s

34.7

TG tok/s

7445

TTFT (ms)

17.8

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 4,096

Performance by Context Length

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

Batching Results

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