<h1 id="qwen-for-minimaxh3-(qp)">Qwen for MinimaxH3 (QP)</h1>NOTE: If you downloaded the day one version I had quantized the wrong files resulting in a lobotimized LLMRequirements:<ol><li>Update <a target="_blank" rel="ugc" href="https://developer.nvidia.com/cuda-downloads">CUDA to 13.4.2</a></li><li>Update <a target="_blank" rel="ugc" href="https://pytorch.org/">Pytorch to 13.2</a></li><li>Update at minimum comfy-aimdo, comfy-kitchen</li><li>Basic <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3337482?fileId=3224058">workflow</a> shows how to use both first frame text guided and first frame last frame with comfy kitchen backend node to speed up generation by 60% (This prevents pyattention fallback which is slow)</li></ol>pytorch version: 2.13.0+cu132xformers version: 0.0.35Using xformers attentionComfyUI version: 0.35.0comfy-aimdo version: 0.5.5comfy-kitchen version: 0.2.34Consider --disable-dynamic-vram if you are having OOM issues after a few generation or crash when trying to use comfy kitchen vs pyattention<hr /><h3 id="qp-(quantization-prediction)">QP (Quantization Prediction)</h3>QP is theoretically improving 40-50% of the blocks on the trailing 16 Matnitsa bits.For the other 50-60% that it does not improve it did not degrade them more then what they would have been rounded to in the first place.This was tested on Full FP32 trainings such as T5.

Qwen for MinimaxH3 (QP) **Fixed INT8, MXFP8, NVFP4**

Files with SHA256: a302d45176a612655917f9e00e55a4af9f620b4464efc549ee2a19e7ec7c5dbc