# LM Studio Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/lm-studio
> Markdown URL: https://aitinkerers.org/technologies/lm-studio.md
> Technology record last updated: 2026-02-26T11:03:04Z
> Generated: 2026-09-23T00:40:02Z

LM Studio is the cross-platform desktop application for downloading, running, and serving local LLMs (Llama, Gemma, Qwen) on macOS, Windows, and Linux.

LM Studio delivers local LLM power directly to your desktop (macOS, Windows, Linux). Use the built-in catalog to discover and download models like Llama 3.1 or Gemma 2 in formats like GGUF and MLX. Run these models offline via a simple chat interface, or expose them over an OpenAI-compatible REST API for seamless integration with your development projects. This is local, private AI: full control, zero cloud dependency.

- Official technology site: https://lmstudio.ai/
- Public AI Tinkerers demos and talks: 8
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Local LLM Orchestration with LangChain & LM Studio](https://manchester-nh.aitinkerers.org/talks/rsvp_J5NYtoRctBU)

Showing a prototype of how I am exploring LLM orchestration toolchains by building the same thing three ways: pure Python, LangChain, and Prompt Flow. The use case is a simple multi-perspective tool that sends a prompt through different 'personality' system prompts and captures the outputs. This is a learning spike, not a polished product—I'll share what I built, what I learned, and where I got stuck.

- Event context: AI Tinkerers – Manchester/Bedford Inaugural Meetup · January 20, 2026 — 2026-01-20 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_J5NYtoRctBU

### [Your Gaming PC, Humanity’s Cloud: A New Vision for AI Infrastructure](https://nyc.aitinkerers.org/talks/rsvp_vFB96_Hru3U)

I’ll be presenting a desktop platform that turns any gaming PC into an OpenAI-compatible GPU server. The goal is to make compute accessible, collaborative, and decentralized — allowing anyone to share their unused GPU power with friends, communities, or the public. The demo will walk through how the platform transforms a local GPU into an API-compatible endpoint, showing how it integrates with the OpenAI API format for seamless use with existing AI clients. I’ll cover the technical architecture, including GPU resource management, real-time job routing, and the underlying stack used for model execution. I’ll also demonstrate running an AI model locally, sharing it within a small peer group, and scaling it into a shared public pool — all with minimal setup. The presentation will emphasize how this approach can democratize AI compute and enable a community-powered alternative to centralized cloud infrastructure.

- Event context: The Future of AI Infrastructure (Ft. Oracle & NVIDIA) — 2025-12-09 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_vFB96_Hru3U

### [NeuroGraph](https://paris.aitinkerers.org/talks/rsvp_BSibVS972M0)

A Graph Builder based on a file or URL

- Event context: Turn Your Knowledge into an API for LLMs - Meetup — 2025-12-09 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_BSibVS972M0

### [AnythingLLM: la plataforma integral para ejecutar modelos LLM locales y agentes de IA](https://manizales.aitinkerers.org/talks/rsvp_WTwy_y5eHg0)

En esta charla presentaremos AnythingLLM, una aplicación de inteligencia artificial todo en uno desarrollada por Mintplex Labs. AnythingLLM permite ejecutar modelos de lenguaje locales, sistemas de recuperación aumentada de información (RAG) y herramientas de agentes de IA sin necesidad de programación ni infraestructura compleja. Mostraremos cómo interactuar con documentos como PDFs, archivos de Word, CSV y bases de código, así como importar documentos desde ubicaciones online. También explicaremos cómo cargar modelos locales en formato GGUF y cómo integrar modelos comerciales de proveedores como OpenAI, Azure o AWS. La plataforma está diseñada para funcionar de forma local por defecto, lo que garantiza que todos los modelos, documentos y conversaciones se almacenen de manera privada en la máquina del usuario.

- Event context: 🏔️ ¡Noveno Encuentro de AI Tinkerers Manizales! — 2025-10-29 — Manizales
- Public talk page: https://manizales.aitinkerers.org/talks/rsvp_WTwy_y5eHg0

### [Pydantic AI & Pydantic Graph - Cooperative and Competitive Agents](https://nashville.aitinkerers.org/talks/rsvp_pXQAQhp-NlM)

Fundamentals of Pydantic AI and Pydantic Graph with examples of cooperative and competitive agents.

- Event context: AI Tinkerers Nashville – October 28th, 2025 — 2025-10-28 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_pXQAQhp-NlM

### [Obsidian Private AI - Talk to Your Journal, Help Process Your Feelings](https://seattle.aitinkerers.org/talks/rsvp__YGHS_aLpqk)

Zuckerberg recently said in a public interview with Dwarkesh that a top usage of AI is to prepare to have a tough conversation with a loved one or a manager. But, I use it to have conversations with someone even more difficult, myself. I really enjoy using ChatGPT and other models for this, however with memories and personalization, it started popping up in my other prompts which made me nervous. Do I want my most private thoughts being stored forever and used for personalization? I journal a lot and wanted to be completely free to express how I feel, and use AI to ask questions that help me think differently. In my journal entries, I ask it. "Talk to this journal entry like a good friend" "Is there another reason for this person's behavior that I'm not seeing?" "Is there something that I'm not seeing as a result of the trauma I've experienced?" "Pretend you are Bill Campbell, the famous coach to Silicon Valley coach, what does this person need to hear?"

- Event context: Building AI Agents with Google Cloud AI — 2025-07-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp__YGHS_aLpqk

### [Talk to your Obsidian Notebooks](https://seattle.aitinkerers.org/talks/rsvp_SyRyq-oqKPw)

I created a Local LLM Plugin for Obsidian that lets you talk to your notes. I write a journal everyday and spend a lot of time copy and pasting things into online LLM's and cringe about my private thoughts being captured and stored forever. I wanted something that was more private and still had the capabilities of a publicly hosted LLM. The part that is crazy, is that I vibe coded the whole thing. I wanted to share the process, the outcome, and how local models for your sensitive data should be part of everyone's workflow.

- Event context: AI Tinkerers Seattle – June Meetup — 2025-06-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_SyRyq-oqKPw

### [Building a Product Powered by Local LLM's Only - Using LLM's in Cursor](https://seattle.aitinkerers.org/talks/rsvp_mXEnxibIEu8)

I wanted to describe my journey that started about 5 months ago upon my first AI Tinkerers event where I was curious to work with LLM's but didn't really know how to get started. After my first event, I got advice to use LM Studio to play with local LLM's to create. I was instantly hooked, but I wanted to put them to work in a way other's hadn't in a privacy sensitive way, using Locally hosted LLM's only. To learn, I had to get creative, and I wanted to use LLM's to help build it in a language I'm not as proficint in, Python. This started an multi-month journey into building games to guess who's a murderer to building a bot that uses Experience Sampling Method (ESM) to capture real-time, contextual data about how people feel during different activities, avoiding the biases of memory recall. The talk will talk about my journey to build the app, the types of things people run into, including dropping $2k on an RTX 4090 Super.

- Event context: AI Tinkerers Seattle - February 2025 Meetup — 2025-02-22 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_mXEnxibIEu8

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 664 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Gemma 3](https://aitinkerers.org/technologies/gemma-3) ([Markdown](https://aitinkerers.org/technologies/gemma-3.md)) — 3 public demos
- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [AnythingLLM](https://aitinkerers.org/technologies/anythingllm) ([Markdown](https://aitinkerers.org/technologies/anythingllm.md)) — 1 public demo
- [claude-4](https://aitinkerers.org/technologies/claude-4) ([Markdown](https://aitinkerers.org/technologies/claude-4.md)) — 8 public demos
- [Cloud Functions for Firebase](https://aitinkerers.org/technologies/cloud-functions-for-firebase) ([Markdown](https://aitinkerers.org/technologies/cloud-functions-for-firebase.md)) — 1 public demo
- [Firebase Realtime Database](https://aitinkerers.org/technologies/firebase-realtime-database) ([Markdown](https://aitinkerers.org/technologies/firebase-realtime-database.md)) — 1 public demo
- [Flutter](https://aitinkerers.org/technologies/flutter) ([Markdown](https://aitinkerers.org/technologies/flutter.md)) — 24 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 446 public demos
- [llama](https://aitinkerers.org/technologies/llama) ([Markdown](https://aitinkerers.org/technologies/llama.md)) — 48 public demos
- [Local LLMs](https://aitinkerers.org/technologies/local-llms) ([Markdown](https://aitinkerers.org/technologies/local-llms.md)) — 2 public demos
- [Neo4j](https://aitinkerers.org/technologies/neo4j) ([Markdown](https://aitinkerers.org/technologies/neo4j.md)) — 29 public demos
- [Nomic](https://aitinkerers.org/technologies/nomic) ([Markdown](https://aitinkerers.org/technologies/nomic.md)) — 1 public demo
- [Obsidian](https://aitinkerers.org/technologies/obsidian) ([Markdown](https://aitinkerers.org/technologies/obsidian.md)) — 6 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Prompt Flow](https://aitinkerers.org/technologies/prompt-flow) ([Markdown](https://aitinkerers.org/technologies/prompt-flow.md)) — 1 public demo
- [Pydantic AI](https://aitinkerers.org/technologies/pydantic-ai) ([Markdown](https://aitinkerers.org/technologies/pydantic-ai.md)) — 7 public demos