← Back to community benchmarks

gemma-4-26b-a4b

M5 Max (40c) · 128 GB · 6bit · 2026-04-03

Performance

4k

tokens

3,567

PP tok/s

56.6

TG tok/s

1149

TTFT (ms)

21.5

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.1

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,726	49.8	20.9 GB	view
4k	3,567	56.6	21.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	49.8	1.00×
2×	28.8	0.58×
4×	60.1	1.21×