# qnguyen3/chat-with-mlx

An all-in-one LLMs Chat UI for Apple Silicon Mac using MLX Framework.

Repository: https://github.com/qnguyen3/chat-with-mlx
Canonical: https://ross.abutalabs.com/products/chat-with-mlx
Homepage: https://twitter.com/stablequan
Language: Python
License: MIT
License Family: permissive
Last push: 2024-09-06T11:47:06+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 66
- inputs: {"age_days": 929, "days_push": 726, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1593, forks 127 (observed 2026-08-28T04:05:08.832042+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: chatbot, llm-inference, rag, ui-components
- domain: large-language-models, chatbots, artificial-intelligence, self-hosted
- platform: python
- tags: apple-silicon, mlx, chat-ui, local-llm, privacy, huggingface, macos, desktop

## Member repositories
- qnguyen3/chat-with-mlx (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:08.832042+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:54:15.399031+00:00, confidence not recorded.
  - readme: https://github.com/qnguyen3/chat-with-mlx (fetched 2026-08-28T04:05:08.832042+00:00, sha 94c23a1574f0)
- Data as of 2026-08-30T08:39:29.467469+00:00.