← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 48 GB · 4bit · 2026-04-07

Performance

1k

tokens

656.3

PP tok/s

65.2

TG tok/s

1560

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.4

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	656.3	65.2	14.2 GB	current
4k	727.4	61.5	14.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	65.2	1.00×
2×	95.5	1.46×
4×	115.5	1.77×