Qwen3.6 27B vs 27B MTP on RTX 3090s | Head-to-Head
In this video, I put Qwen3.6 27B and Qwen3.6 27B MTP head to head on RTX 3090s to see how the regular model compares against the MTP version. Both models were run locally on my AI server using separate 3090 GPUs, and I tested them with the exact same single-file HTML prompts at the same time to compare speed, quality, creativity, interactivity, and how well each model followed instructions. Prompts included: • Interactive lava lamp • Mini aquarium simulator • Tower defense game This is not a perfect scientific benchmark, but it is a real-world side-by-side test to see if the MTP version actually feels faster or better when building creative, interactive browser-based projects from scratch. Models tested: • Qwen3.6 27B • Qwen3.6 27B MTP Hardware: • RTX 3090 GPUs • Local AI server setup • Running both models side by side Let me know which model you think won and what matchup I should test next. #Qwen #Qwen36 #LocalAI #LLM #AIModels #OpenSourceAI #CodingAI #RTX3090 #Homelab #TokenChaser #MTP
Video
Models Tested
Prompts Used
Create a single HTML file for an interactive lava lamp. Colorful blobs should float, merge, stretch, separate, and gently react to my mouse. Make it relaxing, smooth, and visually polished.
Create a single HTML file for a mini aquarium simulator. Fish should swim with different behaviors, plants should sway, bubbles should rise, and I should be able to feed the fish, tap the glass, and change the water color/theme. Make it visually polished and interactive.
Create a single HTML file for a tower defense game. Enemies should follow a path, towers should be placeable with different attack styles, waves should get harder, money should be earned from kills, and the player should be able to upgrade towers between waves. Make it playable, polished, and visually exciting. name it MTPtd.html