Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | AWS Lambda | Node.js | llama.cpp | CTransformers | Text Generation Inference | KoboldCpp | vLLM |
|---|---|---|---|---|---|---|---|---|
| Score | B71 | B-65 | B-65 | C+63 | D46 | F39 | F38 | F35 |
| Type | Language | Serverless | Language | |||||
| Execution | interpreted | hybrid | jit | aot | hybrid | hybrid | hybrid | jit |
| Interface | cli | platform | cli | cli | sdk | api | gui | api |
| Cold Start | 50ms | 200ms | 50ms | 100ms | 800ms | 10000ms | 1500ms | 5000ms |
| Memory | 15MB | 128MB | 40MB | 50MB | 200MB | 2000MB | 400MB | 2000MB |
| Startup | 10ms | 100ms | 20ms | 10ms | 100ms | 5000ms | 300ms | 3000ms |
| Isolation | process | microvm | process | process | process | container | process | process |
| Maturity | production | production | production | production | stable | production | stable | production |
| Languages | Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | JavaScript, TypeScript | C, C++ | Python, C++ | Rust, Python | C++, Python | Python |
| License | Other | Proprietary | MIT | MIT | MIT | Apache-2.0 | AGPL-3.0 | Apache-2.0 |
| Links |