Uploaded May 2026 | Updated September 2026, 2 weeks ago
🚀 The LangChain 10 Days FREE Bootcamp is live: 10 lessons, free AI models only, from your first API call to a production grade RAG agent. Start with Day 0 for the roadmap and setup.
📺 Full playlist: youtube.com/watch?v=KJ3_NExk7-Q&list=PLW4pPr9JCovI&index=1
----------
Qwen 3.6 on Ollama is one of the best local AI coding models right now.
In this video, I test Qwen 3.6 by building real games like Flappy Bird, Snake, and more.
Qwen 3.6 is finally here on Ollama, and the results are honestly shocking. In this video, I tested Qwen 3.6 locally and compared its performance with Gemma 4 — and the difference is huge.
I used simple prompts to generate complete working games like Flappy Bird, Car Racing, and the classic Snake game — all inside a single HTML file. No complex setup, no GPU, and no API cost.
This video also covers:
How Qwen 3.6 performs in real-world coding tasks
Why it beats Gemma 4 in benchmarks and practical use
How to use Qwen 3.6 with Ollama + VS Code Copilot
What makes Mixture of Experts (MoE) architecture so powerful
Why reasoning + tool calling = agentic coding
If you're into local LLMs, AI coding, or building apps without cloud cost, this is a must-watch.
👉 Try it yourself:
Just run:
ollama run qwen:3.6
🚀 What You'll Learn
Build games using AI locally
Use Qwen 3.6 with Ollama
Understand MoE vs Dense architecture
Improve coding with AI agents
🚀 The LangChain 10 Days FREE Bootcamp is live: 10 lessons, free AI models only, from your first API call to a production grade RAG agent. Start with Day 0 for the roadmap and setup.
📺 Full playlist: youtube.com/watch?v=KJ3_NExk7-Q&list=PLW4pPr9JCovI&index=1
----------
Qwen 3.6 on Ollama is one of the best local AI coding models right now.
In this video, I test Qwen 3.6 by building real games like Flappy Bird, Snake, and more.
Qwen 3.6 is finally here on Ollama, and the results are honestly shocking. In this video, I tested Qwen 3.6 locally and compared its performance with Gemma 4 — and the difference is huge.
I used simple prompts to generate complete working games like Flappy Bird, Car Racing, and the classic Snake game — all inside a single HTML file. No complex setup, no GPU, and no API cost.
This video also covers:
How Qwen 3.6 performs in real-world coding tasks
Why it beats Gemma 4 in benchmarks and practical use
How to use Qwen 3.6 with Ollama + VS Code Copilot
What makes Mixture of Experts (MoE) architecture so powerful
Why reasoning + tool calling = agentic coding
If you're into local LLMs, AI coding, or building apps without cloud cost, this is a must-watch.
👉 Try it yourself:
Just run:
ollama run qwen:3.6
🚀 What You'll Learn
Build games using AI locally
Use Qwen 3.6 with Ollama
Understand MoE vs Dense architecture
Improve coding with AI agents
