← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (32c) · 36 GB · 4bit · 2026-04-24

Performance

1k

tokens

926.5

PP tok/s

87.3

TG tok/s

1105

TTFT (ms)

14.3

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.7rc2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	926.5	87.3	14.3 GB	current
4k	1,072	80.6	14.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	87.3	1.00×
2×	135.4	1.55×
4×	168.2	1.93×