Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | GGUF | Python (CPython) | Node.js | ExLlamaV2 |
|---|---|---|---|---|
| Score | A-83 | B71 | B-65 | D47 |
| Type | Language | Language | ||
| Execution | aot | interpreted | jit | aot |
| Interface | embedded | cli | cli | sdk |
| Cold Start | <1ms | 50ms | 50ms | 1000ms |
| Memory | 0MB | 15MB | 40MB | 300MB |
| Startup | <1ms | 10ms | 20ms | 200ms |
| Isolation | process | process | process | process |
| Maturity | production | production | production | stable |
| Languages | Any | Python | JavaScript, TypeScript | Python, C++, CUDA |
| License | MIT | Other | MIT | MIT |
| Links |