← Back to community benchmarks
gemma-4-31B-it
Performance
4k
tokens
199.1
PP tok/s
14.7
TG tok/s
20574
TTFT (ms)
29.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 197.8 | 15.5 | 27.3 GB | view |
| 4k | 199.1 | 14.7 | 29.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.5 | 1.00× |
| 2× | 29.0 | 1.87× |
| 4× | 37.7 | 2.43× |