LiteLLM vs llama.cpp
Facts only. Adjust the shortlist without leaving this page.
| Field | L LiteLLMProxy that translates many model APIs into one OpenAI-shaped client. | L llama.cppC/C++ runtime that made local GGUF models practical. |
|---|---|---|
| Fit. | ||
| Platforms· | Linux, macOS, Windows, Docker | Linux, macOS, Windows |
| Docker· | Yes | No |
| Commercial | yes | yes |
| Catalog. | ||
| Category· | LLM infrastructure | Local AI |
| License | MIT | MIT |
| Language· | Python | C++ |
| Jobs· | LLM gateway, multi-provider proxy | run Llama, CPU inference, embed models |
| Activity. | ||
| Stars· | 30k | 87k |
| Last commit· | Sep 6, 2026 | Sep 7, 2026 |
| Last release· | Aug 29, 2026 | Sep 3, 2026 |
| Links | ProjectGitHubGuide | ProjectGitHubGuide |