# Qwen3 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/qwen3
> Markdown URL: https://aitinkerers.org/technologies/qwen3.md
> Technology record last updated: 2026-02-23T04:19:21Z
> Generated: 2026-09-21T06:44:38Z

Qwen3 is Alibaba Cloud's flagship, open-source LLM series: a high-efficiency model leveraging a Mixture-of-Experts (MoE) architecture and an adaptive Hybrid Thinking Mode.

Qwen3 is a powerful, open-weighted LLM (Apache 2.0) from Alibaba Cloud, engineered for peak performance and efficiency. Its core design features a diverse model lineup, including dense models (0.6B to 32B) and efficient MoE variants like the Qwen3-235B (22B active parameters). The key innovation is the Hybrid Thinking Mode, which dynamically toggles between deep, step-by-step reasoning and fast, non-thinking responses. This model supports an extensive 119 languages and handles long-context tasks up to 128K tokens, making it a robust, versatile choice for advanced multilingual and agentic workflows.

- Official technology site: https://qwen.ai
- Public AI Tinkerers demos and talks: 9
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Goals MCP for preventing agents from reporting "Fake Done"](https://missoula.aitinkerers.org/talks/rsvp_bd91Kk9nVv8)

Show case of the goals mcp ( https://github.com/brucepro/goals_mcp ) in real time on a project using claude code. The primary purpose of the MCP is to prevent an agent from providing a done message when the work has not been completed.

- Event context: AI Tinkerers – Missoula Inaugural Meetup · 26 August 2026 — 2026-08-26 — Missoula
- Public talk page: https://missoula.aitinkerers.org/talks/rsvp_bd91Kk9nVv8

### [Mac Companion](https://islamabad-rawalpindi.aitinkerers.org/talks/rsvp_TJdw2lkaKBQ)

Mac Companion is a native macOS voice agent, with three modes: Transcription (live, Parakeet/Whisper), Companion (notch-anchored async shell), and Assistance (voice-to-tool-calls, coming next)

- Event context: AI Tinkerers Islamabad - July 18, 2026 — 2026-07-18 — Islamabad Rawalpindi
- Public talk page: https://islamabad-rawalpindi.aitinkerers.org/talks/rsvp_TJdw2lkaKBQ

### [What It Actually Takes to Run Your Own AI Server](https://columbus.aitinkerers.org/talks/rsvp_21NDaaY8t6M)

I built a local multi-GPU inference server for running large open models entirely on my own hardware — from scratch, on two RTX 3090s. I'll do a live walkthrough of my original hand-built setup: tabbyAPI serving exllamav3 with Gemma 4 31B dense, including the cache and reasoning config that took real trial and error to get right. Then I'll pivot to ODS (Osmantic Deployment System), a tool I learned about from Ahmad at Osmantic during AI Engineer World's Fair, and demo it live against the same hardware — showing how it auto-detects your GPU and picks its own model (it landed on Qwen 3.5 27B rather than the Gemma model I'd chosen manually), then wires up the full stack (inference, chat UI, RAG, voice, agents) that I spent weeks assembling by hand.

- Event context: AI Tinkerers - Columbus July Meetup — 2026-07-06 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_21NDaaY8t6M

### [Prism: Privacy-First Multi-Model Orchestration](https://dubai.aitinkerers.org/talks/rsvp_gu_mOBH3NEM)

Prism is a privacy-aware AI orchestration layer that decomposes any query into parallel sub-tasks, routes each to the right model (local Qwen3, Groq, or Gemini) based on sensitivity, executes them concurrently via a dependency DAG, then synthesizes a single coherent response — all in one WebSocket-driven interface. Live demo will show: a real query decomposing into 3 parallel tasks, a DAG rendering the execution graph in real-time, the privacy gate redacting secrets before they leave the machine, and a local Qwen3.6-35B running on a laptop GPU via llama.cpp with MoE CPU offload.

- Event context: AI Tinkerers Dubai - June Demo Day — 2026-06-13 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_gu_mOBH3NEM

### [VLMs for Electronics Design](https://raleigh.aitinkerers.org/talks/rsvp_PDqUleDH6rI)

An electronics design tool (think KiCAD or Altium) that leverages VLMs to turn vendor datasheet PDFs into live component models extracted directly from manufacturer reference documentation. The AI Tinkerers demo shows how I built the extraction pipeline using small open weight VLMs deployed on Modal, and a UI built on top of Zed's GPUI framework. The code and benchmark results discussed during the talk are now available on Github as the Parselab project.

- Event context: AI Tinkerers Raleigh Meetup — May 6, 2026 — 2026-05-06 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_PDqUleDH6rI

### [Sarathy &amp; me!](https://ottawa.aitinkerers.org/talks/rsvp_bcfMBtYyxgc)

A openclaw style personal assistant forked from nanobot, inspired from Hermes and openclaw

- Event context: AI Tinkerers Ottawa Meetup — April 25th, 2026 — 2026-04-25 — Ottawa
- Public talk page: https://ottawa.aitinkerers.org/talks/rsvp_bcfMBtYyxgc

### [How To Sell Cards Online (Fast)](https://nurnberg.aitinkerers.org/talks/rsvp_j3cTo9Vft5s)

Automated trading card identification, grading and pricing using local VLMs (Qwen3.5), MLX, prompt caching and visual chain-of-thought - fast, on consumer hardware, without training data.

- Event context: AI Tinkerers Nürnberg: April Meetup — 2026-04-22 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_j3cTo9Vft5s

### [Your Brand Translator](https://paris.aitinkerers.org/talks/rsvp__5FOk0bFKFc)

A personal branch is a must for today's professionals and entrepreneurs. But these same people don't have time to do it themselves and services cost thousands. So we build an agent, - based on OpenClaw for easy interaction via WhatsApp, Telegram and Signal - with a ton of image and video editing tool: IG filters, automatic clipping, deep image generation, caption generation, video from image generation, video modifications, music generation, application of any HF-based model - and the ability to schedule the posts via buffer Share your expertise and experience effortlessly.

- Event context: High-Performance Local AI Development: Kick-off ThinkStation PGX — 2026-03-17 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp__5FOk0bFKFc

### [LLM-Powered Video Editing via Natural Language Scripting with Local Models](https://toronto.aitinkerers.org/talks/rsvp__O4FHg-kOBU)

Live-demoing our video editor leveaging local llms (eg Gemma3/Qwen3 w/ Ollama) for content generation and editing. We'll walk through the core workflow: - generating the initial video structure (narration, image/video sequence defined in our custom JSON spec) from a prompt - editing the video by modifying a human-readable script representation; the LLM translates these natural language changes into precise JSON operations to update the underlying video spec - showing how the editor syncs the script, timeline, and Remotion-based player preview in real-time We'll highlight the technical challenge of reliably mapping freeform text edits to structured JSON modifications and how we use prompt engineering

- Event context: AI Tinkerers Toronto - May 2025 Meetup: AGENTS at Ada — 2025-05-22 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp__O4FHg-kOBU

## Related Technologies

- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [llama](https://aitinkerers.org/technologies/llama) ([Markdown](https://aitinkerers.org/technologies/llama.md)) — 48 public demos
- [MLX](https://aitinkerers.org/technologies/mlx) ([Markdown](https://aitinkerers.org/technologies/mlx.md)) — 7 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [vLLM](https://aitinkerers.org/technologies/vllm) ([Markdown](https://aitinkerers.org/technologies/vllm.md)) — 33 public demos
- [Claude API](https://aitinkerers.org/technologies/claude-api) ([Markdown](https://aitinkerers.org/technologies/claude-api.md)) — 20 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [exllamav3](https://aitinkerers.org/technologies/exllamav3) ([Markdown](https://aitinkerers.org/technologies/exllamav3.md)) — 1 public demo
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [FastAPI WebSockets](https://aitinkerers.org/technologies/fastapi-websockets) ([Markdown](https://aitinkerers.org/technologies/fastapi-websockets.md)) — 1 public demo
- [Gemma3](https://aitinkerers.org/technologies/gemma3) ([Markdown](https://aitinkerers.org/technologies/gemma3.md)) — 1 public demo
- [Gemma 4 31B](https://aitinkerers.org/technologies/gemma-4-31b) ([Markdown](https://aitinkerers.org/technologies/gemma-4-31b.md)) — 1 public demo
- [goals_mcp](https://aitinkerers.org/technologies/goals-mcp) ([Markdown](https://aitinkerers.org/technologies/goals-mcp.md)) — 1 public demo
- [GPT-5](https://aitinkerers.org/technologies/gpt-5) ([Markdown](https://aitinkerers.org/technologies/gpt-5.md)) — 30 public demos
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [Local Inference](https://aitinkerers.org/technologies/local-inference) ([Markdown](https://aitinkerers.org/technologies/local-inference.md)) — 2 public demos
- [macOS](https://aitinkerers.org/technologies/macos) ([Markdown](https://aitinkerers.org/technologies/macos.md)) — 6 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
