← Back to community benchmarks
gemma-4-31b-it
Performance
1k
tokens
83.4
PP tok/s
12.8
TG tok/s
12273
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 83.4 | 12.8 | 17.6 GB | current |
| 4k | 81.9 | 11.5 | 19.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.8 | 1.00× |
| 2× | 18.9 | 1.48× |
| 4× | 20.0 | 1.56× |