← Back to community benchmarks

gemma-4-31b-it-mxfp8

M5 Max (40c) · 128 GB · 8bit · 2026-05-01
Performance
32k
tokens
376.1
PP tok/s
6.8
TG tok/s
87121
TTFT (ms)
38.2
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 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 597.2 14.8 30.9 GB view
4k 514.7 13.9 33.6 GB view
8k 489.8 13.0 34.1 GB view
16k 436.6 12.3 35.3 GB view
32k 376.1 6.8 38.2 GB current
64k 209.4 5.6 44.2 GB view
128k 164.2 4.2 56.2 GB view