← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (32c) · 36 GB · 4bit · 2026-04-13

Performance

1k

tokens

1,515

PP tok/s

94.0

TG tok/s

676

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M5 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,515	94.0	14.2 GB	current
4k	2,231	86.3	14.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	94.0	1.00×
2×	138.8	1.48×
4×	193.6	2.06×