← Back to community benchmarks
gemma-4-31b-it
Performance
4k
tokens
200.8
PP tok/s
21.5
TG tok/s
20400
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 200.1 | 23.8 | 17.6 GB | view |
| 4k | 200.8 | 21.5 | 19.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.8 | 1.00× |
| 2× | 41.1 | 1.73× |
| 4× | 45.5 | 1.91× |