← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-07
Performance
16k
tokens
561.4
PP tok/s
13.3
TG tok/s
29185
TTFT (ms)
36.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 651.0 14.5 33.9 GB view
16k 561.4 13.3 36.1 GB current
32k 516.2 12.3 39.0 GB view
64k 438.0 10.2 45.1 GB view