← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (16c) · 48 GB · 4bit · 2026-05-07

Performance

1k

tokens

1,375

PP tok/s

74.2

TG tok/s

745

TTFT (ms)

14.3

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 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,375	74.2	14.3 GB	current
16k	1,757	61.6	15.4 GB	view
64k	1,271	39.0	17.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	74.2	1.00×
2×	101.2	1.36×
4×	122.9	1.66×