← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 24 GB · 4bit · 2026-04-14

Performance

1k

tokens

370.5

PP tok/s

33.9

TG tok/s

2764

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.5.dev1

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	370.5	33.9	14.2 GB	current
4k	378.8	32.2	14.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.9	1.00×
2×	50.3	1.48×
4×	57.6	1.70×