Qwen 3.6 27B: um modelo LOCAL pode SUBSTITUIR APIs Pagas? (Teste no OpenCode)
Alibaba has released Qwen 3.6 with 27 billion parameters, open source, and official benchmarks show it outperforming Claude 4.5 Opus in Terminal Bench 2.0. Will this hold up in practice? In this video, I test Qwen 3.6 27B Local with 5-bit quantization running on OpenCode in real programming projects on my RTX 5090. Let's see if a local model can create a complete landing page with image reading, an Angry Birds clone in Three.js, and the classic Zelda in 3D. _______ ⚡ Coding Tools: ⏵ GLM - https://z.ai/subscribe?ic=1CUTHGZM5X ⏵ AI Coding Plan - https://www.alibabacloud.com/en/campa... ⏵ Alibaba Cloud - https://www.alibabacloud.com/en/campa... ⚡ TTS ⏵ ElevenLabs - Text-to-Speech: https://try.elevenlabs.io/aiprogbr-tts ⏵ ElevenLabs - Voice Clone: https://try.elevenlabs.io/aiprogbr-vo... ⚡ Hardware ⏵ ZimaBoard 2: https://shop.zimaspace.com/products/z... ⚠️ Use coupon: AIProgBr15 to receive a $15.00 discount ⏵ Dock to connect the Video Card to the ZimaBoard 2: https://shop.zimaspace.com/products/g... _______ 🔹 Want to learn how to create apps from scratch to publication with me? So check out my course: https://programadorbr.com/flutter?src... _______ 0:00 Intro 0:40 Setup 1:00 Landing Page Project 4:45 Angry Birds Project 9:55 Zelda 3D Project 14:09 Conclusion _______ 👀 If you're curious, take a look at some of my published apps: ⏵ Teleprompter: https://apps.apple.com/app/apple-stor... ⏵ Pomodoro: https://apps.apple.com/app/apple-stor... ⏵ Infinite Tic-Tac-Toe iOS: https://apps.apple.com/app/apple-stor... ⏵ Reverse Play iOS: https://apps.apple.com/ca/app/reverse... _______ ✴️ Also follow my other channels: ⏵ Channel about the Apple universe: / @iprogbr ⏵ Programming channel: / @programadorbr ⏵ Instagram profile: / progbr ⏵ Substack profile: https://progbr.substack.com/ Some of the links in this description may be affiliate links, meaning they may generate commission for the channel at no extra cost to you.

The Best Local Agentic Coding Workflow (Complete Guide)

5 local models for those who don't have a NASA computer (and they are excellent)

DFlash Just Made AI 6x Faster : DFlash, DeepSpec Explained

Qwen 3.6 27B is a MONSTER, but can it run locally? I tested it on an RTX 5090 and RTX 5060 Ti and...

I ran Qwen 3.6 35B on 8GB of VRAM at almost 20 t/s (COMPLETE TUTORIAL using llama.cpp)

My PC Setup to Run LOCAL AI for Free Forever, Gemma 4, Qwen 3.6, Llama, LM Studio, GLM 5.2

Kimi K2.7 Code: 5x cheaper than Opus 4.8 and does it come close?

Is Bonsai 27B 1-bit the FUTURE of Local LLMs? (It even runs on PHONES)

The Most Important Conversation in AI Right Now

I tested the Qwen 3.7 Plus Preview and it blew me away (ABSURD quality).

OpenCode Tutorial for Beginners: Setup, Agents, Skills & MCP

No Boss, No Money: The Raw Reality of China’s Gen-Z Freelancers

MORNING PRAYER | Surrender Your Family to God with Faith and Walk this Day in His Peace and Prote...

I tested local models with Ollama: are they ready for everyday use?

Qwen 3.6 35B flavor 200B (running local without quantization)

Gemma 4: o modelo Open Source MAIS esperado de 2026 (Qwen 3.5 perdeu o reinado?)

How to use MTP in llama.cpp to ABSURDLY increase the speed of your local AI

Gemma 2 12B: The local multimodal AI that runs on your computer

Gemma 4, Qwen 3.6, and Granite 4.1: I tested local AIs vs. Claude.

