What’s the strongest model I can train on my MacBook Pro in five minutes? I’ll give the answer upfront: the best 5-minute model I could train was a ~1.8M-param…

Transform your file management with intelligent, automated file renaming powered by AI.

A focused macOS editor for turning specs into software—with Claude Code built in.

A comprehensive guide outlining best practices for building reliable, user-friendly Model Context Protocol (MCP) tools with proper configuration, testing, and release management.

A compelling use case for AI: a Japanese to English translator that gives me a translation, breakdown of the Chinese characters in a Japanese phrase, and the ability to ask follow-up questions.

System prompt for a Raycast chat preset, acting as a Todoist assistant using the new AI Extension. - raycast_chat_preset_instructions.md

We took a closer look at how the top-tier M3 Ultra fares when running the colossal DeepSeek V3 671B parameter model using the popular llama.cpp inference engine. The results paint a picture of…

Interesting release from Google, as a follow-up [to Gemma 3](https://simonwillison.net/2025/Mar/12/gemma-3/) from last month: To make Gemma 3 even more accessible, we are announcing new versions optimized with Quantization-Aware Training …

Learn how to run Qwen3 models locally on your Mac with MLX and create an autonomous coding agent using Localforge - completely free!

DeepSeek R-1 is the most powerful open-source reasoning model that performs on par with OpenAI's o1 model. Run the 1.58-bit Dynamic GGUF version by Unsloth.

Msty is the perfect alternative to LM Studio. Msty offers a powerful and intuitive interface that makes it easy to get started, even for beginners. Say goodbye to complexities and embrace the simplicity with Msty. With innovative features like Folders, Vapor Mode, and Workspaces, Msty makes you more productive than you ever got with LM Studio.

🚀 Want to fine-tune AI models on your Mac without cloud services? As an ex-Ollama developer, I'll show you how to use Apple's MLX framework to fine-tune mod...

BoltAI is a native, high-performance AI app for Mac. It allows you to integrate AI assistances into your daily tasks.

Meta's new Llama 3.3 70B is a genuinely GPT-4 class Large Language Model that runs on my laptop.

MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX. - Blaizzy/mlx-vlm

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚ - exo-explore/exo

Setup your own private Generative AI environment using Ollama

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚ - exo-explore/exo

There’s a whole lot of buzz around the new Qwen2.5-Coder Series of open source (Apache 2.0 licensed) LLM releases from Alibaba’s Qwen research team. On first impression it looks like …

The ultimate AI productivity app that protects your privacy. Bring all your apps and data into one AI-powered search and assistant. Get it for you and for your teams today.

MacWhisper has been updated to version 8 with some new features, including a video player. Multiple apps use the Whisper model to perform transcription. I bought a license for MacWhisper early, and I’ve been using it a lot ever since. One example: We use a Notion database to manage all the MacSparky content (this blog, the... Continue reading →

MindMac let you use ChatGPT efficient on macOS

AI powered voice to text for macOS

An open source approach to locally record and enable searching everything you view on your Apple Silicon. - jasonjmcghee/rem: An open source approach to locally record and enable searching everythi...

archived 5 Nov 2023 01:42:48 UTC

Press a hotkey to chat anywhere on your Mac. No subscription fees. No logins. Your own API key.

The search engine for your life. Find anything you've seen, said, or heard.

MLX: An array framework for Apple silicon. Contribute to ml-explore/mlx development by creating an account on GitHub.