Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | llama.cpp | Docker | CTransformers | Text Generation Inference |
|---|---|---|---|---|
| Score | C+63 | C-54 | D46 | F39 |
| Type | Container | |||
| Execution | aot | hybrid | hybrid | hybrid |
| Interface | cli | cli | sdk | api |
| Cold Start | 100ms | 500ms | 800ms | 10000ms |
| Memory | 50MB | 50MB | 200MB | 2000MB |
| Startup | 10ms | 200ms | 100ms | 5000ms |
| Isolation | process | container | process | container |
| Maturity | production | production | stable | production |
| Languages | C, C++ | Any | Python, C++ | Rust, Python |
| License | MIT | Apache-2.0 | MIT | Apache-2.0 |
| Links |