← Back to community benchmarks

gemma-4-26b-a4b

M4 Pro (20c) · 24 GB · 4bit · 2026-04-05

Performance

4k

tokens

726.7

PP tok/s

57.8

TG tok/s

5638

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 24 GB

GPU Cores 20

Software

oMLX v0.3.4

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	649.9	64.8	14.2 GB	view
4k	726.7	57.8	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	64.8	1.00×
2×	92.4	1.43×
4×	111.9	1.73×