Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Text Generation Inference | KoboldCpp | MLC LLM |
|---|---|---|---|
| Score | F39 | F38 | F38 |
| Type | |||
| Execution | hybrid | hybrid | aot |
| Interface | api | gui | sdk |
| Cold Start | 10000ms | 1500ms | 2000ms |
| Memory | 2000MB | 400MB | 500MB |
| Startup | 5000ms | 300ms | 500ms |
| Isolation | container | process | process |
| Maturity | production | stable | stable |
| Languages | Rust, Python | C++, Python | Python, C++ |
| License | Apache-2.0 | AGPL-3.0 | Apache-2.0 |
| Links |