← Back to community benchmarks

community--gemma-4-26b-a4b-it

M5 Pro (20c) · 64 GB · 4bit · 2026-07-05

Performance

1k

tokens

1,377

PP tok/s

79.0

TG tok/s

744

TTFT (ms)

14.3

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4

macOS macOS 27.0

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,377	79.0	14.3 GB	current
4k	1,584	76.0	14.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	79.0	1.00×
2×	106.2	1.34×
4×	136.0	1.72×