← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-15
Performance
64k
tokens
266.1
PP tok/s
6.5
TG tok/s
246310
TTFT (ms)
45.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 346.7 12.3 31.8 GB view
4k 418.1 12.1 34.5 GB view
16k 423.7 10.8 35.8 GB view
32k 355.4 8.0 39.1 GB view
64k 266.1 6.5 45.1 GB current
128k 198.5 5.3 57.1 GB view
Batching Results
Batch Size TG tok/s Speedup
12.3 1.00×
16.3 1.33×
22.5 1.83×