Qwen 3.8 Max Full COURSE 1 HOUR (Build & Automate Anything)
Deepseek v4.1 Flash vs Qwen 3.8
Tested Qwen 3.8 flash for our beloved pelican.
The results look good but it was slowwwww af It took around an hour for this. I think I'll stick to DeepSeek V4.1 flash ✌︎㋡
Another test of my 2bit Qwen 3.8 27B.
A good example of the difference between standard 2-bit and our Opti compression on a task that is multi-faceted and requires different tooling. Standard llama.cpp IQ2_M (9.3 GiB): The “turtle” is basically a sparse point cloud over a grid,
You have reached the end of the archive
All of qwen38