Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | CUDA Runtime | AWS Lambda | Node.js | llama.cpp | Candle | CTransformers | KoboldCpp |
|---|---|---|---|---|---|---|---|---|
| Score | B71 | B-65 | B-65 | B-65 | C+63 | D48 | D46 | F38 |
| Type | Language | Serverless | Language | |||||
| Execution | interpreted | aot | hybrid | jit | aot | jit | hybrid | hybrid |
| Interface | cli | sdk | platform | cli | cli | sdk | sdk | gui |
| Cold Start | 50ms | 100ms | 200ms | 50ms | 100ms | 300ms | 800ms | 1500ms |
| Memory | 15MB | 500MB | 128MB | 40MB | 50MB | 200MB | 200MB | 400MB |
| Startup | 10ms | 50ms | 100ms | 20ms | 10ms | 50ms | 100ms | 300ms |
| Isolation | process | hardware | microvm | process | process | process | process | process |
| Maturity | production | production | production | production | production | stable | stable | stable |
| Languages | Python | C, C++, Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | JavaScript, TypeScript | C, C++ | Rust | Python, C++ | C++, Python |
| License | Other | Proprietary | Proprietary | MIT | MIT | Apache-2.0 | MIT | AGPL-3.0 |
| Links |