Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | Python (CPython) | AWS Lambda | llama.cpp | Docker | ONNX Runtime | KoboldCpp |
|---|---|---|---|---|---|---|---|
| Score | A-83 | B71 | B-65 | C+63 | C-54 | C-50 | F38 |
| Type | Language | Serverless | Container | ||||
| Execution | aot | interpreted | hybrid | aot | hybrid | hybrid | hybrid |
| Interface | embedded | cli | platform | cli | cli | sdk | gui |
| Cold Start | <1ms | 50ms | 200ms | 100ms | 500ms | 500ms | 1500ms |
| Memory | 0MB | 15MB | 128MB | 50MB | 50MB | 300MB | 400MB |
| Startup | <1ms | 10ms | 100ms | 10ms | 200ms | 100ms | 300ms |
| Isolation | process | process | microvm | process | container | process | process |
| Maturity | production | production | production | production | production | production | stable |
| Languages | Any | Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | C, C++ | Any | Python, C++, C#, Java | C++, Python |
| License | MIT | Other | Proprietary | MIT | Apache-2.0 | MIT | AGPL-3.0 |
| Links |