← Back to community benchmarks
translategemma-4b-it
Performance
8k
tokens
2,543
PP tok/s
57.4
TG tok/s
3221
TTFT (ms)
9.1
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 | 1,850 | 33.0 | 8.7 GB | view |
| 4k | 2,341 | 52.2 | 8.9 GB | view |
| 8k | 2,543 | 57.4 | 9.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.0 | 1.00× |
| 2× | 36.2 | 1.10× |
| 4× | 60.1 | 1.82× |