← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (16c) · 48 GB · 8bit · 2026-04-03

Performance

4k

tokens

1,584

PP tok/s

41.3

TG tok/s

2585

TTFT (ms)

27.3

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.1

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,649	42.9	26.8 GB	view
4k	1,584	41.3	27.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	42.9	1.00×
2×	53.3	1.24×
4×	74.9	1.75×