Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | AWS Lambda | ExLlamaV2 | Text Generation Inference | KoboldCpp |
|---|---|---|---|---|
| Score | B-65 | D47 | F39 | F38 |
| Type | Serverless | |||
| Execution | hybrid | aot | hybrid | hybrid |
| Interface | platform | sdk | api | gui |
| Cold Start | 200ms | 1000ms | 10000ms | 1500ms |
| Memory | 128MB | 300MB | 2000MB | 400MB |
| Startup | 100ms | 200ms | 5000ms | 300ms |
| Isolation | microvm | process | container | process |
| Maturity | production | stable | production | stable |
| Languages | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | Python, C++, CUDA | Rust, Python | C++, Python |
| License | Proprietary | MIT | Apache-2.0 | AGPL-3.0 |
| Links |