Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | ExLlamaV2 | MLX | KoboldCpp |
|---|---|---|---|---|
| Score | B71 | D47 | D47 | F38 |
| Type | Language | |||
| Execution | interpreted | aot | jit | hybrid |
| Interface | cli | sdk | sdk | gui |
| Cold Start | 50ms | 1000ms | 500ms | 1500ms |
| Memory | 15MB | 300MB | 200MB | 400MB |
| Startup | 10ms | 200ms | 100ms | 300ms |
| Isolation | process | process | process | process |
| Maturity | production | stable | stable | stable |
| Languages | Python | Python, C++, CUDA | Python, C++, Swift | C++, Python |
| License | Other | MIT | MIT | AGPL-3.0 |
| Links |