Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | CUDA Runtime | AWS Lambda | llama.cpp | llamafile |
|---|---|---|---|---|
| Score | B-65 | B-65 | C+63 | C-53 |
| Type | Serverless | |||
| Execution | aot | hybrid | aot | aot |
| Interface | sdk | platform | cli | cli |
| Cold Start | 100ms | 200ms | 100ms | 500ms |
| Memory | 500MB | 128MB | 50MB | 100MB |
| Startup | 50ms | 100ms | 10ms | 50ms |
| Isolation | hardware | microvm | process | process |
| Maturity | production | production | production | stable |
| Languages | C, C++, Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | C, C++ | C, C++ |
| License | Proprietary | Proprietary | MIT | Apache-2.0 |
| Links |