← Back to community benchmarks

gemma-4-31b-it

M5 Max (40c) · 128 GB · bf16 · 2026-04-05
Performance
16k
tokens
646.4
PP tok/s
6.0
TG tok/s
25345
TTFT (ms)
61.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.3.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 746.8 7.1 60.7 GB view
8k 738.8 6.8 61.0 GB view
16k 646.4 6.0 61.7 GB current
32k 597.1 5.4 64.0 GB view