← Back to community benchmarks

gemma-4-31B-it-oQ8

M5 Max (40c) · 128 GB · 8bit · 2026-05-30

Performance

64k

tokens

451.5

PP tok/s

10.6

TG tok/s

145158

TTFT (ms)

43.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.12

macOS macOS 26.5

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	634.4	31.4	34.0 GB	view
64k	451.5	10.6	43.9 GB	current