← Back to community benchmarks
gemma-4-31b-it
Performance
32k
tokens
535.1
PP tok/s
8.1
TG tok/s
61238
TTFT (ms)
37.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 535.1 | 8.1 | 37.4 GB | current |
| 195k | 203.7 | 1.4 | 61.3 GB | view |