Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | ExLlamaV2 | KoboldCpp |
|---|---|---|---|
| Score | A-83 | D47 | F38 |
| Type | |||
| Execution | aot | aot | hybrid |
| Interface | embedded | sdk | gui |
| Cold Start | <1ms | 1000ms | 1500ms |
| Memory | 0MB | 300MB | 400MB |
| Startup | <1ms | 200ms | 300ms |
| Isolation | process | process | process |
| Maturity | production | stable | stable |
| Languages | Any | Python, C++, CUDA | C++, Python |
| License | MIT | MIT | AGPL-3.0 |
| Links |