← Back to community benchmarks

gemma-4-31b-it-mxfp8

M4 Max (40c) · 128 GB · 8bit · 2026-04-17
Performance
32k
tokens
163.3
PP tok/s
5.3
TG tok/s
200641
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.3
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 173.0 9.6 33.8 GB view
32k 163.3 5.3 36.2 GB current
64k 140.4 3.5 40.9 GB view