← Back to community benchmarks

gemma-4-26B-A4B-it-heretic

M5 Max (40c) · 64 GB · 4bit · 2026-04-25

Performance

4k

tokens

2,241

PP tok/s

102.6

TG tok/s

1828

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,242	110.2	14.3 GB	view
4k	2,241	102.6	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	110.2	1.00×
2×	146.9	1.33×
4×	195.9	1.78×