← Back to community benchmarks
gemma-4-31B-it
Performance
32k
tokens
529.2
PP tok/s
13.6
TG tok/s
61922
TTFT (ms)
34.4
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
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 571.7 | 16.3 | 27.3 GB | view |
| 4k | 613.4 | 16.9 | 29.9 GB | view |
| 8k | 609.5 | 16.3 | 30.4 GB | view |
| 16k | 571.5 | 15.1 | 31.6 GB | view |
| 32k | 529.2 | 13.6 | 34.4 GB | current |
| 64k | 445.8 | 11.2 | 40.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.3 | 1.00× |
| 2× | 28.3 | 1.74× |
| 4× | 38.1 | 2.34× |
| 8× | 44.7 | 2.74× |