← Back to community benchmarks
translategemma-12b-it
Performance
8k
tokens
853.8
PP tok/s
15.7
TG tok/s
9596
TTFT (ms)
24.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 866.6 | 25.0 | 23.4 GB | view |
| 4k | 834.5 | 24.4 | 24.3 GB | view |
| 8k | 853.8 | 15.7 | 24.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.0 | 1.00× |
| 2× | 28.5 | 1.14× |
| 4× | 54.8 | 2.19× |