← Back to community benchmarks
gemma-4-31b-it
Performance
4k
tokens
162.1
PP tok/s
16.7
TG tok/s
25273
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 162.7 | 18.2 | 17.6 GB | view |
| 4k | 162.1 | 16.7 | 19.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.2 | 1.00× |
| 2× | 33.0 | 1.81× |
| 4× | 36.9 | 2.03× |