← Back to community benchmarks
gemma-4-31b-it
Performance
32k
tokens
178.4
PP tok/s
18.7
TG tok/s
183663
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 178.4 | 18.7 | 22.8 GB | current |
| 64k | 156.2 | 15.0 | 30.8 GB | view |