← Back to community benchmarks
gemma-4-31b-5bit
Performance
4k
tokens
179.4
PP tok/s
18.7
TG tok/s
22837
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.3.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 175.9 | 20.3 | 21.4 GB | view |
| 4k | 179.4 | 18.7 | 22.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.3 | 1.00× |
| 2× | 26.7 | 1.32× |
| 4× | 31.0 | 1.53× |