← Back to community benchmarks
gemma-4-31B-it
Performance
4k
tokens
88.0
PP tok/s
6.9
TG tok/s
46526
TTFT (ms)
34.5
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 96.0 | 7.0 | 31.8 GB | view |
| 4k | 88.0 | 6.9 | 34.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.0 | 1.00× |
| 2× | 13.3 | 1.90× |
| 4× | 17.5 | 2.50× |