Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | containerd | AWS Lambda | llama.cpp | Docker | ExLlamaV2 | KoboldCpp |
|---|---|---|---|---|---|---|---|
| Score | B71 | B-66 | B-65 | C+63 | C-54 | D47 | F38 |
| Type | Language | Container | Serverless | Container | |||
| Execution | interpreted | hybrid | hybrid | aot | hybrid | aot | hybrid |
| Interface | cli | platform | platform | cli | cli | sdk | gui |
| Cold Start | 50ms | 100ms | 200ms | 100ms | 500ms | 1000ms | 1500ms |
| Memory | 15MB | 20MB | 128MB | 50MB | 50MB | 300MB | 400MB |
| Startup | 10ms | 20ms | 100ms | 10ms | 200ms | 200ms | 300ms |
| Isolation | process | container | microvm | process | container | process | process |
| Maturity | production | production | production | production | production | stable | stable |
| Languages | Python | Any | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | C, C++ | Any | Python, C++, CUDA | C++, Python |
| License | Other | Apache-2.0 | Proprietary | MIT | Apache-2.0 | MIT | AGPL-3.0 |
| Links |