← Back to community benchmarks

gemma-4-26B-A4B-it-RotorQuant

M1 Max (32c) · 32 GB · 4bit · 2026-05-16

Performance

64k

tokens

347.0

PP tok/s

21.8

TG tok/s

188874

TTFT (ms)

17.7

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.9.dev1

macOS macOS 15.1

Context 65,536