← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (16c) · 48 GB · 8bit · 2026-04-18

Performance

4k

tokens

1,583

PP tok/s

49.3

TG tok/s

2588

TTFT (ms)

26.2

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,156	51.2	25.7 GB	view
4k	1,583	49.3	26.2 GB	current
8k	1,665	44.7	26.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	51.2	1.00×
2×	73.3	1.43×
4×	91.2	1.78×