Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | CUDA Runtime | Node.js | llama.cpp | ONNX Runtime | Ollama |
|---|---|---|---|---|---|---|
| Score | B71 | B-65 | B-65 | C+63 | C-50 | D49 |
| Type | Language | Language | ||||
| Execution | interpreted | aot | jit | aot | hybrid | hybrid |
| Interface | cli | sdk | cli | cli | sdk | cli |
| Cold Start | 50ms | 100ms | 50ms | 100ms | 500ms | 1000ms |
| Memory | 15MB | 500MB | 40MB | 50MB | 300MB | 500MB |
| Startup | 10ms | 50ms | 20ms | 10ms | 100ms | 100ms |
| Isolation | process | hardware | process | process | process | process |
| Maturity | production | production | production | production | production | production |
| Languages | Python | C, C++, Python | JavaScript, TypeScript | C, C++ | Python, C++, C#, Java | Python, JavaScript, Go |
| License | Other | Proprietary | MIT | MIT | MIT | MIT |
| Links |