← Back to community benchmarks

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

M4 (10c) · 24 GB · 4bit · 2026-04-29

Performance

4k

tokens

257.1

PP tok/s

12.4

TG tok/s

15930

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.8rc1

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	286.8	28.1	14.2 GB	view
4k	257.1	12.4	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.1	1.00×
2×	26.5	0.94×
4×	24.5	0.87×