Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | AWS Lambda | llama.cpp | ONNX Runtime |
|---|---|---|---|---|
| Score | A-83 | B-65 | C+63 | C-50 |
| Type | Serverless | |||
| Execution | aot | hybrid | aot | hybrid |
| Interface | embedded | platform | cli | sdk |
| Cold Start | <1ms | 200ms | 100ms | 500ms |
| Memory | 0MB | 128MB | 50MB | 300MB |
| Startup | <1ms | 100ms | 10ms | 100ms |
| Isolation | process | microvm | process | process |
| Maturity | production | production | production | production |
| Languages | Any | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | C, C++ | Python, C++, C#, Java |
| License | MIT | Proprietary | MIT | MIT |
| Links |