Hi guys, Back again. I have tested the Qwen 3.6 UD 2 K_XL Unsloth model on the same paper to web app task. The model is performing very well. It handled all tool calls properly and also managed large context using llama.cpp on a 16GB VRAM on lapt…
Note: First is Qwen3.5 35B MoE (Left) and Second is Qwen3.6 (Right) Hi Guys Just did quick comparison of Qwen3.6 35B MoE against Qwen 3.5 35B MoE. with reasoning off using llama.cpp and same quant unsloth 4 K_XL GGUF First is Qwen3.5 outcome and…
Last time I posted on how this model has performed in creating the webapp based on provided research paper. I got so much love to see people has appreciated the post and of-course the potential of this MOE model. I am sharing details on how I use…