RTX 5060 TI + Qwen 3.6: setup "acessível" que roda IA de alto nível

I tested the Qwen 3.6 35B (Mixture of Experts, 3B active) with 3-bit quantization on an RTX 5060 TI graphics card with 16GB of VRAM to find out if it's worth it. Result: 77 tokens per second, working vision, functional code, and proof that this is one of the best local models available, costing much less hardware than you might imagine. In the Artificial Analysis benchmark, the Qwen 3.6 35B surpasses the Qwen 3.5 with 122B and comes very close to the Qwen 3.5 with 397B, which has 10 times more parameters. The comparison with the Kimi K2.5 with 1 trillion parameters is also impressive. _______ ⚡ 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... ⚡ 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... _______ 🔹 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 0:20 Documentation 4:37 ZimaBoard Setup 6:53 Speed ​​of Inference 8:00 Vision Test 9:05 Description Generation 12:09 Website Creation 14:28 Flappy Bird _______ 👀 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.

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

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)
▶︎

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

LFM 2.5: The New AI That Fits Into 1GB of RAM
▶︎

LFM 2.5: The New AI That Fits Into 1GB of RAM

The Non-NVIDIA AI Card Everyone’s Ignoring
▶︎

The Non-NVIDIA AI Card Everyone’s Ignoring

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

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

Qwen 3.6 27B: Can a LOCAL model REPLACE paid APIs? (Tested on OpenCode)
▶︎

Qwen 3.6 27B: Can a LOCAL model REPLACE paid APIs? (Tested on OpenCode)

AMD Ryzen AI Max 128GB is NOT worth it for local LLM.
▶︎

AMD Ryzen AI Max 128GB is NOT worth it for local LLM.

RTX Spark: NVIDIA is trying to HIDE a detail that changes EVERYTHING for local LLMs
▶︎

RTX Spark: NVIDIA is trying to HIDE a detail that changes EVERYTHING for local LLMs

Will the Intel Arc Pro B70 32GB replace the Nvidia RTX 5090? I tested it with LLM and image gener...
▶︎

Will the Intel Arc Pro B70 32GB replace the Nvidia RTX 5090? I tested it with LLM and image gener...

The Most Important Conversation in AI Right Now
▶︎

The Most Important Conversation in AI Right Now

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

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

I Tested the Cheapest Path to 96GB of VRAM
▶︎

I Tested the Cheapest Path to 96GB of VRAM

A 744B AI Model Runs On A Laptop With No GPU
▶︎

A 744B AI Model Runs On A Laptop With No GPU

DAS kommt nach KI-Agenten: Die nächste Stufe der KI beginnt JETZT
▶︎

DAS kommt nach KI-Agenten: Die nächste Stufe der KI beginnt JETZT

CHOSEN ONE!! YOUR IDENTITY REVEAL JUST SHOOK THE INTERNET... AND THEIR MINDS
▶︎

CHOSEN ONE!! YOUR IDENTITY REVEAL JUST SHOOK THE INTERNET... AND THEIR MINDS

FORGET CHATGPT! Build a FREE Local AI using an Orange Pi 🧠
▶︎

FORGET CHATGPT! Build a FREE Local AI using an Orange Pi 🧠

The Guide to Local LLMs: You Don't Have to Be Stuck on Anthropic
▶︎

The Guide to Local LLMs: You Don't Have to Be Stuck on Anthropic

DONT Buy these GPU's for Local AI! (learn from my mistake)
▶︎

DONT Buy these GPU's for Local AI! (learn from my mistake)

Esse cubo TRANSFORMOU minha forma de rodar IA local (ZimaCube 2 Pro)
▶︎

Esse cubo TRANSFORMOU minha forma de rodar IA local (ZimaCube 2 Pro)

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

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