Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | gVisor | Python (CPython) | CUDA Runtime | llama.cpp |
|---|---|---|---|---|
| Score | B72 | B71 | B-65 | C+63 |
| Type | MicroVM | Language | ||
| Execution | hybrid | interpreted | aot | aot |
| Interface | cli | cli | sdk | cli |
| Cold Start | 50ms | 50ms | 100ms | 100ms |
| Memory | 20MB | 15MB | 500MB | 50MB |
| Startup | 30ms | 10ms | 50ms | 10ms |
| Isolation | microvm | process | hardware | process |
| Maturity | stable | production | production | production |
| Languages | Any | Python | C, C++, Python | C, C++ |
| License | Apache-2.0 | Other | Proprietary | MIT |
| Links |