← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (16c) · 48 GB · 8bit · 2026-05-03

Performance

4k

tokens

1,611

PP tok/s

49.8

TG tok/s

2542

TTFT (ms)

26.4

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,279	51.5	25.8 GB	view
4k	1,611	49.8	26.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	51.5	1.00×
8×	107.9	2.10×