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