Colibri Tutorial: Run Big Models Like DeepSeek, Qwen on One GPU Locally
This video is a hands-on local tutorial on new colibri v2.1.0 locally. 📬Weekly AI Newsletter: https://fahdmirza.substack.com/ 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: https://bit.ly/fahd-mirza Coupon code: FahdMirza 🔥 Buy Me a Coffee to support the channel: https://ko-fi.com/fahdmirza #colibri PLEASE FOLLOW ME: ▶ LinkedIn: / fahdmirza ▶ YouTube: / @fahdmirza ▶ Blog: https://www.fahdmirza.com 0:00 Intro: what colibri is 0:20 What's new in v2.1 0:40 What we will do in this video 1:00 System Configuration 1:10 Install and setup (Qwen3.6-35B-A3B) 2:05 Concept diagram: how colibri places a model 3:20 First chat and speed test 5:00 New chat UI, monitor and profiling 5:59 System One, expert map and models page 8:57 Running a GGUF as published (Flint) 10:35 Trying a bigger model (DeepSeek V4 Flash, 91 GB) 12:45 Wrap up RESOURCES: ▶ https://github.com/JustVugg/colibri All rights reserved © Fahd Mirza
