← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 4bit · 2026-04-17

Performance

4k

tokens

253.6

PP tok/s

25.7

TG tok/s

16152

TTFT (ms)

14.6

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.5.dev2

macOS macOS 15.7.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	241.7	27.2	14.2 GB	view
4k	253.6	25.7	14.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.2	1.00×
2×	33.4	1.23×
4×	67.1	2.47×