# Qwen3 Coder Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/qwen3-coder
> Markdown URL: https://aitinkerers.org/technologies/qwen3-coder.md
> Technology record last updated: 2026-02-24T03:36:40Z
> Generated: 2026-09-20T21:45:55Z

Qwen3-Coder is the most agentic open-source code MoE model, featuring 480B total parameters and a 1M token context window for repo-scale development.

This is the Qwen team's flagship agentic coding model, setting new state-of-the-art results among open models (comparable to Claude Sonnet 4). The Qwen3-Coder-480B-A35B-Instruct variant leverages a Mixture-of-Experts (MoE) architecture: 480 billion total parameters with only 35 billion active per token for efficiency. Crucially, it handles massive codebases with a native 256K context, extendable to 1M tokens, enabling true Agentic Coding, Browser-Use, and Tool-Use for complex, multi-turn software engineering tasks.

- Official technology site: https://github.com/QwenLM/Qwen3-Coder
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Confidential Computing on Multi-GPUs](https://sf.aitinkerers.org/talks/rsvp_ID1Y9xB9IF4)

What was required to run large models such as Deepseek R1 and Qwen3 Coder inside secure hardware enclaves on NVIDIA GPUs and how this wasn’t possible until very recently

- Event context: AI Infra Jam: Demos That Weren’t Possible Two Months Ago — 2025-09-25 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_ID1Y9xB9IF4

### [How to use Qwen3-Coder (or any other LLM) with Claude Code](https://munich.aitinkerers.org/talks/rsvp_tpX-SXAb2Io)

A simple way for Claude Code users to switch from the costly Claude models to the newly released SOTA open-source/weights coding model, Qwen3-Coder, or any other LLM, locally or online.

- Event context: AI Tinkerers Munich - July 25 — 2025-07-25 — Munich
- Public talk page: https://munich.aitinkerers.org/talks/rsvp_tpX-SXAb2Io

## Related Technologies

- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Deepseek R1](https://aitinkerers.org/technologies/deepseek-r1) ([Markdown](https://aitinkerers.org/technologies/deepseek-r1.md)) — 6 public demos
- [LiteLLM](https://aitinkerers.org/technologies/litellm) ([Markdown](https://aitinkerers.org/technologies/litellm.md)) — 21 public demos
- [NVIDIA H200](https://aitinkerers.org/technologies/nvidia-h200) ([Markdown](https://aitinkerers.org/technologies/nvidia-h200.md)) — 1 public demo
- [OpenRouter](https://aitinkerers.org/technologies/openrouter) ([Markdown](https://aitinkerers.org/technologies/openrouter.md)) — 33 public demos
- [vLLM](https://aitinkerers.org/technologies/vllm) ([Markdown](https://aitinkerers.org/technologies/vllm.md)) — 33 public demos