Qwen 3.6 27B MTP vs Qwopus 3.6 27B v2 MTP - 16GB Local LLM setup

In this video I am testing Qwen 3.6 27B MTP against Qwopus 3.6 27B v2 MTP. Let's see how the base Qwen model compares to the same model fine tuned on Opus reasoning.

Both models are running on a local AI PC I have built with 16GB VRAM and 32GB DDR4 RAM.

I run the models through a coding test suite consisting of three tests:
1. Expense Tracker
2. Card Matching Game
3. Breakout Game
4. 2D Driving Game

If you're interested in local LLMs, AI and homelabs from the perspective of a software engineer with many years of professional experience working with LLMs in production - feel free to subscribe!

Qwen: https://huggingface.co/unsloth/Qwen3.6-27B-MTP-GGUF
Qwopus: https://huggingface.co/Jackrong/Qwopus3.6-27B-v2-MTP-GGUF
GitHub: https://github.com/lukesdevlab/youtube
Patreon: https://www.patreon.com/cw/LukesDevLab

#localllm #localai #qwen #homelab #llamacpp #homelab #qwopus #opus #mtp #v2

Chapters:
0:00 Intro
0:12 Models
0:51 Tests
1:38 System Specs
2:00 Expense Tracker - Qwen
5:28 Expense Tracker - Qwopus
7:38 Match Game - Qwen
9:17 Match Game - Qwopus
11:19 Breakout - Qwen
13:12 Breakout - Qwopus
14:54 Driving Game - Qwen
17:23 Driving Game - Qwopus
20:21 Conclusion

Видео Qwen 3.6 27B MTP vs Qwopus 3.6 27B v2 MTP - 16GB Local LLM setup канала Luke's Dev Lab