← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 4bit · 2026-04-13

Performance

8k

tokens

3,486

PP tok/s

94.9

TG tok/s

2350

TTFT (ms)

14.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.5.dev1

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,215	114.4	14.2 GB	view
4k	3,347	108.1	14.7 GB	view
8k	3,486	94.9	14.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	114.4	1.00×
2×	167.8	1.47×
4×	224.1	1.96×