← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (20c) · 64 GB · 4bit · 2026-05-05

Performance

4k

tokens

1,688

PP tok/s

71.5

TG tok/s

2426

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,097	75.1	14.3 GB	view
4k	1,688	71.5	14.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	75.1	1.00×
2×	109.1	1.45×
4×	137.3	1.83×