Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | Python (CPython) | AWS Lambda | Podman | KoboldCpp |
|---|---|---|---|---|---|
| Score | A-83 | B71 | B-65 | C57 | F38 |
| Type | Language | Serverless | Container | ||
| Execution | aot | interpreted | hybrid | hybrid | hybrid |
| Interface | embedded | cli | platform | cli | gui |
| Cold Start | <1ms | 50ms | 200ms | 200ms | 1500ms |
| Memory | 0MB | 15MB | 128MB | 50MB | 400MB |
| Startup | <1ms | 10ms | 100ms | 100ms | 300ms |
| Isolation | process | process | microvm | container | process |
| Maturity | production | production | production | stable | stable |
| Languages | Any | Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | Any | C++, Python |
| License | MIT | Other | Proprietary | Apache-2.0 | AGPL-3.0 |
| Links |