← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-13
Performance
1k
tokens
563.5
PP tok/s
14.3
TG tok/s
1817
TTFT (ms)
31.8
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 563.5 14.3 31.8 GB current
4k 553.8 14.0 34.5 GB view
8k 533.8 13.2 35.0 GB view
16k 503.1 12.6 36.1 GB view
32k 438.5 10.5 39.1 GB view
64k 333.2 8.2 45.1 GB view
Batching Results
Batch Size TG tok/s Speedup
14.3 1.00×
20.1 1.41×
26.9 1.88×