Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | Node.js | llama.cpp | Google Cloud Functions | ROCm | Text Generation Inference | KoboldCpp |
|---|---|---|---|---|---|---|---|
| Score | B71 | B-65 | C+63 | C59 | C56 | F39 | F38 |
| Type | Language | Language | Serverless | ||||
| Execution | interpreted | jit | aot | hybrid | aot | hybrid | hybrid |
| Interface | cli | cli | cli | platform | sdk | api | gui |
| Cold Start | 50ms | 50ms | 100ms | 300ms | 200ms | 10000ms | 1500ms |
| Memory | 15MB | 40MB | 50MB | 128MB | 600MB | 2000MB | 400MB |
| Startup | 10ms | 20ms | 10ms | 50ms | 100ms | 5000ms | 300ms |
| Isolation | process | process | process | container | hardware | container | process |
| Maturity | production | production | production | production | stable | production | stable |
| Languages | Python | JavaScript, TypeScript | C, C++ | Python, JavaScript, TypeScript, Go, Java, Ruby, PHP | C, C++, Python | Rust, Python | C++, Python |
| License | Other | MIT | MIT | Proprietary | MIT | Apache-2.0 | AGPL-3.0 |
| Links |