← Back to community benchmarks
gemma-4-31b-it
Performance
4k
tokens
77.5
PP tok/s
7.8
TG tok/s
52833
TTFT (ms)
33.6
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.3.4
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 86.2 | 9.5 | 31.8 GB | view |
| 4k | 77.5 | 7.8 | 33.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.5 | 1.00× |
| 2× | 7.6 | 0.80× |
| 4× | 18.2 | 1.92× |