← Back to community benchmarks
gemma-4-31b-it
Performance
4k
tokens
22.5
PP tok/s
2.0
TG tok/s
181955
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.9
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 23.9 | 2.1 | 17.6 GB | view |
| 4k | 22.5 | 2.0 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 2.1 | 1.00× |
| 2× | 3.3 | 1.57× |
| 4× | 4.4 | 2.10× |