← Back to community benchmarks

gemma-4-31B-it-uncensored-abliterix4bit-mixed_4_6

M5 Max (40c) · 128 GB · 4bit · 2026-05-15

Performance

64k

tokens

436.4

PP tok/s

12.8

TG tok/s

150168

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536