← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Pro (16c) · 32 GB · 4bit · 2026-04-13

Performance

1k

tokens

236.8

PP tok/s

35.9

TG tok/s

4324

TTFT (ms)

13.5

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.5.dev1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	236.8	35.9	13.5 GB	current
4k	259.5	33.6	13.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	35.9	1.00×
2×	42.1	1.17×
4×	45.4	1.26×