Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | Python (CPython) | ROCm | Text Generation Inference |
|---|---|---|---|---|
| Score | A-83 | B71 | C56 | F39 |
| Type | Language | |||
| Execution | aot | interpreted | aot | hybrid |
| Interface | embedded | cli | sdk | api |
| Cold Start | <1ms | 50ms | 200ms | 10000ms |
| Memory | 0MB | 15MB | 600MB | 2000MB |
| Startup | <1ms | 10ms | 100ms | 5000ms |
| Isolation | process | process | hardware | container |
| Maturity | production | production | stable | production |
| Languages | Any | Python | C, C++, Python | Rust, Python |
| License | MIT | Other | MIT | Apache-2.0 |
| Links |