← Back to community benchmarks

gemma-4-26B-A4B-it-heretic

M1 Max (24c) · 64 GB · 4bit · 2026-04-17

Performance

1k

tokens

343.0

PP tok/s

47.8

TG tok/s

2985

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.6

macOS macOS 15.7.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	343.0	47.8	14.2 GB	current
4k	370.3	42.9	14.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	47.8	1.00×
2×	59.2	1.24×
4×	70.5	1.47×