← Back to community benchmarks

gemma-4-26B-uncensoredq8

M5 Max (40c) · 128 GB · 8bit · 2026-04-24

Performance

4k

tokens

2,482

PP tok/s

80.1

TG tok/s

1650

TTFT (ms)

54.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,079	84.5	53.7 GB	view
4k	2,482	80.1	54.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	84.5	1.00×
2×	119.6	1.42×
4×	163.3	1.93×