← Back to community benchmarks

gemma-4-31b-it-mxfp8

M4 Max (40c) · 128 GB · 8bit · 2026-04-17
Performance
16k
tokens
173.0
PP tok/s
9.6
TG tok/s
94682
TTFT (ms)
33.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 173.0 9.6 33.8 GB current
32k 163.3 5.3 36.2 GB view
64k 140.4 3.5 40.9 GB view