← Back to community benchmarks

gemma-4-31b-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-01
Performance
64k
tokens
345.7
PP tok/s
12.3
TG tok/s
189553
TTFT (ms)
27.5
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 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 675.3 26.1 17.6 GB view
4k 711.6 25.2 19.7 GB view
8k 686.6 24.0 21.3 GB view
16k 595.2 21.6 21.9 GB view
32k 505.4 14.9 24.8 GB view
64k 345.7 12.3 27.5 GB current
Batching Results
Batch Size TG tok/s Speedup
26.1 1.00×
29.9 1.15×
36.2 1.39×
40.1 1.54×