← Back to community benchmarks
gemma-4-31B-it
Performance
4k
tokens
531.3
PP tok/s
14.6
TG tok/s
7710
TTFT (ms)
34.5
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 615.8 | 15.3 | 31.8 GB | view |
| 4k | 531.3 | 14.6 | 34.5 GB | current |
| 8k | 505.6 | 13.2 | 35.0 GB | view |
| 16k | 446.9 | 11.5 | 36.1 GB | view |
| 32k | 333.0 | 4.7 | 39.3 GB | view |
| 64k | 210.7 | 5.7 | 45.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.3 | 1.00× |
| 2× | 13.1 | 0.86× |
| 4× | 18.4 | 1.20× |
| 8× | 22.8 | 1.49× |