← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 6bit · 2026-05-05
Performance
128k
tokens
327.2
PP tok/s
7.8
TG tok/s
400543
TTFT (ms)
54.8
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 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 583.5 16.2 29.5 GB view
4k 617.0 15.8 32.2 GB view
64k 453.3 10.6 39.5 GB view
128k 327.2 7.8 54.8 GB current
Batching Results
Batch Size TG tok/s Speedup
16.2 1.00×
25.9 1.60×
34.6 2.14×
40.3 2.49×