← Back to community benchmarks

Gemma-4-26B-A4B-IT-UD-Q4_K_XL

M1 Max (32c) · 32 GB · 4bit · 2026-05-18

Performance

64k

tokens

308.1

PP tok/s

16.1

TG tok/s

212720

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536