← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 24 GB · 4bit · 2026-05-12

Performance

4k

tokens

742.7

PP tok/s

65.0

TG tok/s

5515

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 24 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	692.6	67.5	14.3 GB	view
4k	742.7	65.0	14.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	67.5	1.00×
2×	97.1	1.44×
4×	116.0	1.72×