# Turbo-LLM

> Self-hosted local LLM platform running any engine with auto-tuning, real measured tokens/sec, and OpenAI/Anthropic APIs for Claude Code.

- **Category:** LLM Inference
- **Licence:** FSL-1.1-ALv2
- **Latest version:** v1.14.5
- **Open source:** source_available
- **Languages:** Typescript
- **Platforms:** Docker, Linux, Windows, macOS, Android, NPM
- **Tags:** Mcp, Offline, LLM, Inference, Gguf, Gpu, AI, Source available, Self Hosted, Openai Api, Offline First, Claude code, Local llm, Coding agent, Anthropic api, Llama Cpp, Llama Server, Auto Tuning

## Description

TurboLLM is a self-hosted local LLM platform that runs any inference engine — llama.cpp, community forks, vLLM, MLX, KoboldCpp, llamafile, and more — auto-tuned to your GPU. It provides a polished web UI and both OpenAI- and Anthropic-compatible APIs, enabling tools like Claude Code to run against local models with one command. Key features include benchmark-based auto-tuning with VRAM-fit verdicts before you commit, actual generation speed measured on your machine, a model-loading gateway that automatically loads models when requested and keeps favorites ready, a local coding agent with LSP integration, MCP server integrations, ComfyUI GPU sharing, live hardware monitoring, and a native Android app. It runs via npm (npx turbollm), Docker with NVIDIA/AMD GPU support, or native installers on Windows, macOS, and Linux. The project is source-available under FSL-1.1-ALv2 (converting to Apache-2.0 after two years).

## Links

- [Homepage](https://github.com/mohitsoni48/Turbo-LLM)
- [Website](https://turbollm.dev)
- [Documentation](https://turbollm.dev/docs)
- [GitHub](https://github.com/mohitsoni48/TurboLLM)
- [Discord](https://discord.gg/v6kRbV7nC)
- [npm](https://www.npmjs.com/package/turbollm)
- [YouTube](https://www.youtube.com/@TurboLLM)
- [Models hub](https://turbollm.dev/models)
- [Integrations](https://turbollm.dev/integrations)
- [Contributor Programme](https://turbollm.dev/contributor_program)

---
Source: https://selfhost.directory/project/turbo-llm