← Back to community benchmarks
gemma-4-31b-it
Performance
4k
tokens
54.7
PP tok/s
8.8
TG tok/s
74921
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 55.8 | 9.4 | 17.6 GB | view |
| 4k | 54.7 | 8.8 | 19.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.4 | 1.00× |
| 2× | 10.9 | 1.16× |
| 4× | 12.3 | 1.31× |