← Back to community benchmarks
gemma-4-31B-it
Performance
128k
tokens
143.2
PP tok/s
1.6
TG tok/s
915500
TTFT (ms)
51.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.8.dev1
macOS
macOS 26.4.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 246.9 | 18.2 | 31.8 GB | view |
| 64k | 187.5 | 3.2 | 42.5 GB | view |
| 128k | 143.2 | 1.6 | 51.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.2 | 1.00× |
| 2× | 29.8 | 1.64× |
| 4× | 37.1 | 2.04× |
| 8× | 41.1 | 2.26× |