qnguyen3/chat-with-mlx

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1593 stars · 127 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A chat playground application for running LLMs locally on Apple Silicon Macs using Apple's MLX framework. It provides a chat UI with support for HuggingFace and MLX-compatible open-source models, plus document and YouTube-based RAG features.

Use cases

• chat with local llms on mac
• run llama or mistral on apple silicon
• private offline chatbot ui
• chat with pdf documents locally
• query youtube videos with llm
• test open-source models without cloud

When to choose

• you have an Apple Silicon Mac and want local LLM inference
• you want a privacy-focused chat UI without sending data to cloud APIs
• you want to experiment with MLX-compatible models from HuggingFace
• you need simple document Q&A with a local vector database

When to avoid

• you are on Linux or Windows since MLX requires Apple Silicon
• you need production-grade multi-user chat deployment
• you need GPU acceleration on non-Apple hardware
• you need polished, bug-free document indexing workflows

Facets

application · maturity active

chatbot llm-inference rag ui-components large-language-models chatbots artificial-intelligence self-hosted python apple-silicon mlx chat-ui local-llm privacy huggingface macos desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="qnguyen3/chat-with-mlx")