Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | Python (CPython) | containerd | AWS Lambda | ROCm | KoboldCpp |
|---|---|---|---|---|---|---|
| Score | A-83 | B71 | B-66 | B-65 | C56 | F38 |
| Type | Language | Container | Serverless | |||
| Execution | aot | interpreted | hybrid | hybrid | aot | hybrid |
| Interface | embedded | cli | platform | platform | sdk | gui |
| Cold Start | <1ms | 50ms | 100ms | 200ms | 200ms | 1500ms |
| Memory | 0MB | 15MB | 20MB | 128MB | 600MB | 400MB |
| Startup | <1ms | 10ms | 20ms | 100ms | 100ms | 300ms |
| Isolation | process | process | container | microvm | hardware | process |
| Maturity | production | production | production | production | stable | stable |
| Languages | Any | Python | Any | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | C, C++, Python | C++, Python |
| License | MIT | Other | Apache-2.0 | Proprietary | MIT | AGPL-3.0 |
| Links |