Vibe Coding Discover

AI Tools

Bonsai-demo

View on GitHub

Bonsai Demo

★ 3.1K338 forksShellApache-2.0PrismML-Eng

Scripts and setup files for running Bonsai, Ternary-Bonsai, and Bonsai 2 models locally with llama.cpp or MLX. Includes Open WebUI integration, vision support, tool calling, and MCP connections.

Use Cases

Run quantized language models locallyChat with local models through a web UIAnalyze images and PDFsUse model tool callingConnect MCP servers to local-model chatsServe models through an OpenAI-style API

Built With

Language
Shell
Frameworks
llama.cpp · MLX · Open WebUI

Tags

local LLM · small models · quantized models · ternary weights · 1-bit weights · vision-language · tool calling · MCP · offline inference · OpenAI-compatible API