Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | llama.cpp | Google Cloud Functions | ONNX Runtime |
|---|---|---|---|
| Score | C+63 | C59 | C-50 |
| Type | Serverless | ||
| Execution | aot | hybrid | hybrid |
| Interface | cli | platform | sdk |
| Cold Start | 100ms | 300ms | 500ms |
| Memory | 50MB | 128MB | 300MB |
| Startup | 10ms | 50ms | 100ms |
| Isolation | process | container | process |
| Maturity | production | production | production |
| Languages | C, C++ | Python, JavaScript, TypeScript, Go, Java, Ruby, PHP | Python, C++, C#, Java |
| License | MIT | Proprietary | MIT |
| Links |