Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | containerd | llama.cpp | Text Generation Inference | KoboldCpp |
|---|---|---|---|---|
| Score | B-66 | C+63 | F39 | F38 |
| Type | Container | |||
| Execution | hybrid | aot | hybrid | hybrid |
| Interface | platform | cli | api | gui |
| Cold Start | 100ms | 100ms | 10000ms | 1500ms |
| Memory | 20MB | 50MB | 2000MB | 400MB |
| Startup | 20ms | 10ms | 5000ms | 300ms |
| Isolation | container | process | container | process |
| Maturity | production | production | production | stable |
| Languages | Any | C, C++ | Rust, Python | C++, Python |
| License | Apache-2.0 | MIT | Apache-2.0 | AGPL-3.0 |
| Links |