← Back to community benchmarks
gemma-4-31b-it
Performance
4k
tokens
172.3
PP tok/s
19.9
TG tok/s
23774
TTFT (ms)
18.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 196.7 | 16.2 | 16.7 GB | view |
| 4k | 172.3 | 19.9 | 18.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.2 | 1.00× |
| 2× | 29.9 | 1.85× |
| 4× | 32.4 | 2.00× |