← Back to community benchmarks
gemma-4-31b-it
Performance
4k
tokens
173.4
PP tok/s
17.3
TG tok/s
23619
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 173.7 | 18.3 | 17.6 GB | view |
| 4k | 173.4 | 17.3 | 19.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.3 | 1.00× |
| 2× | 28.8 | 1.57× |
| 4× | 34.7 | 1.90× |
| 8× | 25.5 | 1.39× |