← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 8bit · 2026-06-01
Performance
16k
tokens
438.8
PP tok/s
9.5
TG tok/s
37339
TTFT (ms)
36.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 561.4 12.3 31.8 GB view
4k 483.6 11.8 34.6 GB view
8k 475.1 11.1 35.4 GB view
16k 438.8 9.5 36.6 GB current
32k 234.7 5.6 39.8 GB view
64k 215.5 5.3 45.1 GB view
Batching Results
Batch Size TG tok/s Speedup
12.3 1.00×
12.8 1.04×
17.3 1.41×