← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Max (30c) · 32 GB · 4bit · 2026-05-18

Performance

4k

tokens

497.2

PP tok/s

61.9

TG tok/s

8239

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 32 GB

GPU Cores 30

Software

oMLX v0.3.9.dev1

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	468.3	64.9	14.3 GB	view
4k	497.2	61.9	14.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	64.9	1.00×
2×	82.6	1.27×
4×	96.0	1.48×