← Back to community benchmarks

community:gemma-4-26b-a4b-it

M4 Max (40c) · 64 GB · 4bit · 2026-05-18

Performance

4k

tokens

1,341

PP tok/s

99.4

TG tok/s

3055

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,134	103.9	14.3 GB	view
4k	1,341	99.4	14.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	103.9	1.00×
2×	153.4	1.48×
4×	197.0	1.90×