← Back to community benchmarks
gemma-4-31b-it
Performance
1k
tokens
651.8
PP tok/s
26.2
TG tok/s
1571
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 651.8 | 26.2 | 17.6 GB | current |
| 4k | 705.4 | 24.6 | 19.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.2 | 1.00× |
| 2× | 41.3 | 1.58× |
| 4× | 52.4 | 2.00× |
| 8× | 55.3 | 2.11× |