# Qwen 3 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/qwen-3
> Markdown URL: https://aitinkerers.org/technologies/qwen-3.md
> Technology record last updated: 2026-03-16T19:34:27Z
> Generated: 2026-09-21T23:51:11Z

Qwen 3: Alibaba Cloud's flagship, open-source (Apache 2.0) LLM series, featuring a hybrid Mixture-of-Experts (MoE) architecture and dual-mode reasoning for balancing speed and complexity.

This is Qwen 3 (Tongyi Qianwen), Alibaba Cloud's latest open-source language model series. It utilizes a hybrid architecture, including MoE variants like the Qwen3-235B-A22B (22B active parameters), to deliver high performance with efficiency. The core innovation is the Hybrid Reasoning Engine: developers can toggle between 'Thinking Mode' for complex, multi-step tasks (like coding or math) and 'Non-Thinking Mode' for rapid, direct responses. Qwen 3 is built for global deployment, supporting 119 languages and featuring a substantial 128K token context window across many of its models.

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

## Recent Public Talks and Demos

### [\[UofT\] Print Anything: Building the Pipeline from Natural Language to 3D Object](https://toronto.aitinkerers.org/talks/rsvp_z0pA85I3o0k)

What if you could 3D print something simply by describing it in plain English, just as you ask ChatGPT a question? That is the idea behind our project. Our system fine-tunes a Qwen 3 model with LoRA in Google Colab to generate ImplicitCAD code from natural language prompts. The generated code is then compiled into STL files, which can be used for 3D printing. ImplicitCAD is a code-based CAD tool, similar to OpenSCAD. Many people in the 3D printing community like it because script-based design allows precise and reproducible measurements. However, the downside is that users need to know how to write code. To address this, we built a two-phase training pipeline. In the first phase, the model learns ImplicitCAD syntax using real examples collected and filtered from the Thingiverse dataset on HuggingFace. This helps the model understand how 3D geometry is written in code. In the second phase, we introduce logical and spatial reasoning problems so the model can go beyond simple pattern matching. In addition to the model, we also built a web-based preview environment and a Dockerized version of ImplicitCAD. This removes the usual edit-compile-wait workflow that makes these tools difficult to use. The project is meant to be a starting point that future teams can build on and extend.

- Event context: AI Tinkerers Toronto - March - hosted by Mozilla! — 2026-03-25 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_z0pA85I3o0k

## Related Technologies

- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [HuggingFace](https://aitinkerers.org/technologies/huggingface) ([Markdown](https://aitinkerers.org/technologies/huggingface.md)) — 7 public demos
- [LoRA](https://aitinkerers.org/technologies/lora) ([Markdown](https://aitinkerers.org/technologies/lora.md)) — 17 public demos
- [Three](https://aitinkerers.org/technologies/three) ([Markdown](https://aitinkerers.org/technologies/three.md)) — 13 public demos