← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-05-14

Performance

4k

tokens

517.9

PP tok/s

54.9

TG tok/s

7908

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	449.4	56.0	14.3 GB	view
4k	517.9	54.9	14.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	56.0	1.00×
2×	78.3	1.40×
4×	79.1	1.41×