Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Cloudflare Workers | Python (CPython) | CUDA Runtime | Node.js | llama.cpp | CTransformers | KoboldCpp |
|---|---|---|---|---|---|---|---|
| Score | B+75 | B71 | B-65 | B-65 | C+63 | D46 | F38 |
| Type | Edge | Language | Language | ||||
| Execution | jit | interpreted | aot | jit | aot | hybrid | hybrid |
| Interface | platform | cli | sdk | cli | cli | sdk | gui |
| Cold Start | <1ms | 50ms | 100ms | 50ms | 100ms | 800ms | 1500ms |
| Memory | 128MB | 15MB | 500MB | 40MB | 50MB | 200MB | 400MB |
| Startup | <1ms | 10ms | 50ms | 20ms | 10ms | 100ms | 300ms |
| Isolation | process | process | hardware | process | process | process | process |
| Maturity | production | production | production | production | production | stable | stable |
| Languages | JavaScript, TypeScript, Rust, C, C++ | Python | C, C++, Python | JavaScript, TypeScript | C, C++ | Python, C++ | C++, Python |
| License | Proprietary | Other | Proprietary | MIT | MIT | MIT | AGPL-3.0 |
| Links |