← Back to community benchmarks

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

M4 Pro (20c) · 64 GB · 4bit · 2026-04-12

Performance

4k

tokens

748.5

PP tok/s

63.9

TG tok/s

5472

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	690.5	66.8	14.2 GB	view
4k	748.5	63.9	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	66.8	1.00×
2×	96.8	1.45×
4×	116.1	1.74×