kaitchup/

Qwen3.6-27B-autoround-nvfp4-linearattn-mtp-BF16

This is Qwen/Qwen3.6-27B quantized with AutoRound to NVFP4 with linear-attention and MTP layers kept in 16-bit. The model is compatible with vLLM (tested: v0.19). Tested with an RTX Pro 6000. Currently under evaluation. Similar quantization with Qwen3.5 worked very well.

uv pip install vllm
uv pip install git+https://github.com/huggingface/transformers.git