Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | llama.cpp | KoboldCpp | vLLM | Jan |
|---|---|---|---|---|---|
| Score | B71 | C+63 | F38 | F35 | F34 |
| Type | Language | ||||
| Execution | interpreted | aot | hybrid | jit | hybrid |
| Interface | cli | cli | gui | api | gui |
| Cold Start | 50ms | 100ms | 1500ms | 5000ms | 2000ms |
| Memory | 15MB | 50MB | 400MB | 2000MB | 600MB |
| Startup | 10ms | 10ms | 300ms | 3000ms | 400ms |
| Isolation | process | process | process | process | process |
| Maturity | production | production | stable | production | stable |
| Languages | Python | C, C++ | C++, Python | Python | TypeScript, Python |
| License | Other | MIT | AGPL-3.0 | Apache-2.0 | AGPL-3.0 |
| Links |