Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | CUDA Runtime | Node.js | Vulkan | llama.cpp | KoboldCpp |
|---|---|---|---|---|---|---|
| Score | B71 | B-65 | B-65 | C+64 | C+63 | F38 |
| Type | Language | Language | ||||
| Execution | interpreted | aot | jit | aot | aot | hybrid |
| Interface | cli | sdk | cli | sdk | cli | gui |
| Cold Start | 50ms | 100ms | 50ms | 100ms | 100ms | 1500ms |
| Memory | 15MB | 500MB | 40MB | 200MB | 50MB | 400MB |
| Startup | 10ms | 50ms | 20ms | 30ms | 10ms | 300ms |
| Isolation | process | hardware | process | hardware | process | process |
| Maturity | production | production | production | production | production | stable |
| Languages | Python | C, C++, Python | JavaScript, TypeScript | C, C++ | C, C++ | C++, Python |
| License | Other | Proprietary | MIT | Apache-2.0 | MIT | AGPL-3.0 |
| Links |