Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | Python (CPython) | AWS Lambda | Node.js | llama.cpp | Text Generation Inference |
|---|---|---|---|---|---|---|
| Score | A-83 | B71 | B-65 | B-65 | C+63 | F39 |
| Type | Language | Serverless | Language | |||
| Execution | aot | interpreted | hybrid | jit | aot | hybrid |
| Interface | embedded | cli | platform | cli | cli | api |
| Cold Start | <1ms | 50ms | 200ms | 50ms | 100ms | 10000ms |
| Memory | 0MB | 15MB | 128MB | 40MB | 50MB | 2000MB |
| Startup | <1ms | 10ms | 100ms | 20ms | 10ms | 5000ms |
| Isolation | process | process | microvm | process | process | container |
| Maturity | production | production | production | production | production | production |
| Languages | Any | Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | JavaScript, TypeScript | C, C++ | Rust, Python |
| License | MIT | Other | Proprietary | MIT | MIT | Apache-2.0 |
| Links |