← Back to community benchmarks

gemma-4-21b-REAP-Tool-Calling

M4 Pro (16c) · 24 GB · 4bit · 2026-05-23

Performance

64k

tokens

418.7

PP tok/s

36.2

TG tok/s

156533

TTFT (ms)

15.9

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.9

macOS macOS 15.7.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	517.4	51.4	13.4 GB	view
64k	418.7	36.2	15.9 GB	current