← Back to community benchmarks

gemma-4-26B-A4B-it-Claude-Opus-Distill-v2-qx64-hi

M4 Pro (20c) · 48 GB · 6bit · 2026-04-16

Performance

4k

tokens

736.0

PP tok/s

61.0

TG tok/s

5565

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.4

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	674.0	64.2	15.3 GB	view
4k	736.0	61.0	15.8 GB	current
8k	736.5	54.0	15.9 GB	view
16k	698.2	40.0	16.3 GB	view