Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | CUDA Runtime | LLM (Python CLI) |
|---|---|---|---|
| Score | A-83 | B-65 | D49 |
| Type | |||
| Execution | aot | aot | hybrid |
| Interface | embedded | sdk | cli |
| Cold Start | <1ms | 100ms | 500ms |
| Memory | 0MB | 500MB | 100MB |
| Startup | <1ms | 50ms | 100ms |
| Isolation | process | hardware | process |
| Maturity | production | production | stable |
| Languages | Any | C, C++, Python | Python |
| License | MIT | Proprietary | Apache-2.0 |
| Links |