← Back to community benchmarks
gemma-4-31B-it
Performance
1k
tokens
614.3
PP tok/s
15.4
TG tok/s
1667
TTFT (ms)
31.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 614.3 | 15.4 | 31.8 GB | current |
| 64k | 458.0 | 10.3 | 41.8 GB | view |
| 128k | 284.2 | 6.9 | 57.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.4 | 1.00× |
| 4× | 53.9 | 3.50× |