← Back to community benchmarks

gemma-4-26b-a4b-it

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

Performance

16k

tokens

1,757

PP tok/s

61.6

TG tok/s

9327

TTFT (ms)

15.4

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 16,384

Performance by Context Length

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