← Back to community benchmarks

gemma-4-26B-A4B-it-TurboQuant

M5 Pro (20c) · 64 GB · 4bit · 2026-05-09

Performance

64k

tokens

1,417

PP tok/s

33.8

TG tok/s

46248

TTFT (ms)

17.7

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	2,073	67.0	14.8 GB	view
64k	1,417	33.8	17.7 GB	current