Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | llama.cpp | Text Generation Inference | MLC LLM |
|---|---|---|---|---|
| Score | B71 | C+63 | F39 | F38 |
| Type | Language | |||
| Execution | interpreted | aot | hybrid | aot |
| Interface | cli | cli | api | sdk |
| Cold Start | 50ms | 100ms | 10000ms | 2000ms |
| Memory | 15MB | 50MB | 2000MB | 500MB |
| Startup | 10ms | 10ms | 5000ms | 500ms |
| Isolation | process | process | container | process |
| Maturity | production | production | production | stable |
| Languages | Python | C, C++ | Rust, Python | Python, C++ |
| License | Other | MIT | Apache-2.0 | Apache-2.0 |
| Links |