← Back to community benchmarks
translategemma-4b-it
Performance
64k
tokens
4,226
PP tok/s
56.5
TG tok/s
15509
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.20.dev1
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,446 | 160.4 | 2.9 GB | view |
| 4k | 3,949 | 150.1 | 3.1 GB | view |
| 8k | 4,919 | 135.8 | 3.2 GB | view |
| 32k | 4,748 | 84.2 | 4.1 GB | view |
| 64k | 4,226 | 56.5 | 5.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 160.4 | 1.00× |
| 2× | 276.6 | 1.72× |
| 4× | 395.9 | 2.47× |
| 8× | 448.5 | 2.80× |