Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | Python (CPython) | CUDA Runtime | AWS Lambda | Docker |
|---|---|---|---|---|---|
| Score | A-83 | B71 | B-65 | B-65 | C-54 |
| Type | Language | Serverless | Container | ||
| Execution | aot | interpreted | aot | hybrid | hybrid |
| Interface | embedded | cli | sdk | platform | cli |
| Cold Start | <1ms | 50ms | 100ms | 200ms | 500ms |
| Memory | 0MB | 15MB | 500MB | 128MB | 50MB |
| Startup | <1ms | 10ms | 50ms | 100ms | 200ms |
| Isolation | process | process | hardware | microvm | container |
| Maturity | production | production | production | production | production |
| Languages | Any | Python | C, C++, Python | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | Any |
| License | MIT | Other | Proprietary | Proprietary | Apache-2.0 |
| Links |