← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Pro (16c) · 32 GB · 4bit · 2026-04-15

Performance

1k

tokens

235.9

PP tok/s

36.5

TG tok/s

4341

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.4

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	235.9	36.5	14.2 GB	current
4k	249.2	33.7	14.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	36.5	1.00×
2×	44.4	1.22×
4×	49.2	1.35×