← Back to community benchmarks
gemma-4-31b-it
Performance
8k
tokens
158.6
PP tok/s
7.8
TG tok/s
51662
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 162.4 | 18.0 | 17.6 GB | view |
| 4k | 161.5 | 12.5 | 19.5 GB | view |
| 8k | 158.6 | 7.8 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.0 | 1.00× |
| 2× | 32.8 | 1.82× |
| 4× | 36.1 | 2.01× |
| 8× | 37.9 | 2.11× |