← Back to community benchmarks
gemma-4-31b-it
Performance
8k
tokens
506.9
PP tok/s
15.5
TG tok/s
16160
TTFT (ms)
19.6
Peak mem (GB)
Hardware
Chip
M5 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 535.1 | 20.6 | 17.6 GB | view |
| 4k | 513.7 | 18.1 | 19.3 GB | view |
| 8k | 506.9 | 15.5 | 19.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.6 | 1.00× |
| 2× | 33.8 | 1.64× |
| 4× | 38.0 | 1.84× |