Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | Firecracker | CUDA Runtime | AWS Lambda | llama.cpp |
|---|---|---|---|---|---|
| Score | B71 | B70 | B-65 | B-65 | C+63 |
| Type | Language | MicroVM | Serverless | ||
| Execution | interpreted | aot | aot | hybrid | aot |
| Interface | cli | api | sdk | platform | cli |
| Cold Start | 50ms | 125ms | 100ms | 200ms | 100ms |
| Memory | 15MB | 5MB | 500MB | 128MB | 50MB |
| Startup | 10ms | 100ms | 50ms | 100ms | 10ms |
| Isolation | process | microvm | hardware | microvm | process |
| Maturity | production | production | production | production | production |
| Languages | Python | Any | C, C++, Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | C, C++ |
| License | Other | Apache-2.0 | Proprietary | Proprietary | MIT |
| Links |