← Back to community benchmarks
gemma-4-31b-it
Performance
1k
tokens
51.8
PP tok/s
5.6
TG tok/s
19756
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 51.8 | 5.6 | 17.4 GB | current |
| 4k | 50.8 | 5.3 | 19.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.6 | 1.00× |
| 2× | 10.6 | 1.89× |
| 4× | 12.1 | 2.16× |