← Back to community benchmarks

gemma-4-26b-a4b

M5 Pro (20c) · 48 GB · 4bit · 2026-06-04

Performance

4k

tokens

1,908

PP tok/s

70.2

TG tok/s

2148

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.4.1

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,094	72.9	13.6 GB	view
4k	1,908	70.2	14.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	72.9	1.00×
2×	103.7	1.42×
4×	127.2	1.74×