Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | ONNX Runtime | Text Generation Inference |
|---|---|---|---|
| Score | A-83 | C-50 | F39 |
| Type | |||
| Execution | aot | hybrid | hybrid |
| Interface | embedded | sdk | api |
| Cold Start | <1ms | 500ms | 10000ms |
| Memory | 0MB | 300MB | 2000MB |
| Startup | <1ms | 100ms | 5000ms |
| Isolation | process | process | container |
| Maturity | production | production | production |
| Languages | Any | Python, C++, C#, Java | Rust, Python |
| License | MIT | MIT | Apache-2.0 |
| Links |