AI is happening. The future is updating.MiniMax-H3
- https://huggingface.co/MiniMaxAI/MiniMax-H3 - https://huggingface.co/lightx2v/Minimax-h3-Turbo The Qwen3-VL-32B `nvfp4_awq` quant is converted from: https://huggingface.co/cybermotaz/Qwen3-VL-32B-Instruct-NVFP4 For diffusion models prefer `int8_convrot` if you are able to use pytorch with cu130.
- https://huggingface.co/MiniMaxAI/MiniMax-H3 - https://huggingface.co/lightx2v/Minimax-h3-Turbo The Qwen3-VL-32B `nvfp4_awq` quant is converted from: https://huggingface.co/cybermotaz/Qwen3-VL-32B-Instruct-NVFP4 For diffusion models prefer `int8_convrot` if you are able to use pytorch with cu130.