Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | KoboldCpp | MLC LLM | vLLM |
|---|---|---|---|---|
| Score | B71 | F38 | F38 | F35 |
| Type | Language | |||
| Execution | interpreted | hybrid | aot | jit |
| Interface | cli | gui | sdk | api |
| Cold Start | 50ms | 1500ms | 2000ms | 5000ms |
| Memory | 15MB | 400MB | 500MB | 2000MB |
| Startup | 10ms | 300ms | 500ms | 3000ms |
| Isolation | process | process | process | process |
| Maturity | production | stable | stable | production |
| Languages | Python | C++, Python | Python, C++ | Python |
| License | Other | AGPL-3.0 | Apache-2.0 | Apache-2.0 |
| Links |