Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | llama.cpp | CTransformers | Text Generation Inference | KoboldCpp |
|---|---|---|---|---|
| Score | C+63 | D46 | F39 | F38 |
| Type | ||||
| Execution | aot | hybrid | hybrid | hybrid |
| Interface | cli | sdk | api | gui |
| Cold Start | 100ms | 800ms | 10000ms | 1500ms |
| Memory | 50MB | 200MB | 2000MB | 400MB |
| Startup | 10ms | 100ms | 5000ms | 300ms |
| Isolation | process | process | container | process |
| Maturity | production | stable | production | stable |
| Languages | C, C++ | Python, C++ | Rust, Python | C++, Python |
| License | MIT | MIT | Apache-2.0 | AGPL-3.0 |
| Links |