Running Qwen 3.8 Flash Next NVFP4 on one RTX 6000 Pro 96GB.
$2/hr if you need some quick work done
So impressed with what I get from Qwen 3.8 Flash Next at 2.5bpw EXL3!
Demo/recordings of prompts given to DeepSeek Harness Desktop Design and create a very creative, elaborate, and detailed voxel art scene of a pagoda in a beautiful garden with trees, including some cherry
I keep pushing to see how far Qwen 3.8 27B goes
Now we build a Superhot with Minecraft aesthetics I didn't give him any images this time to make the decisions. Very surprised with the quality. None of them were one-shots but they are something great
Splash just launched for Apple Silicon, and it's claiming to run Qwen 3.8 27B twice as fast as anything else on a Mac.
This is a full breakdown of Splash, the new open source local inference engine from inco_ai , built specifically around two models: Qwen 3.8 27B and Qwen 3.6
You have reached the end of the archive
All of qwen38