← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (16c) · 48 GB · 8bit · 2026-04-03

Performance

1k

tokens

1,649

PP tok/s

42.9

TG tok/s

621

TTFT (ms)

26.8

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,649	42.9	26.8 GB	current
4k	1,584	41.3	27.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	42.9	1.00×
2×	53.3	1.24×
4×	74.9	1.75×