← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-04-15

Performance

4k

tokens

602.9

PP tok/s

56.5

TG tok/s

6794

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.5.dev1

macOS macOS 15.7.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	566.2	63.8	14.2 GB	view
4k	602.9	56.5	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	63.8	1.00×
2×	85.3	1.34×
4×	98.7	1.55×