rzgar/Qwen3.8-27B-NVFP4-ComfyUI
ComfyUI node update (Sep 17, 2026):
Fix nvfp4 vision-tower crash with image/video input on ComfyUI 0.35.1+:
the vision tower now stays on the full-precision path instead of being switched
to W4A4 nvfp4 matmul (which can't take the float32 vision activations).
Qwen3.8-27B ComfyUI NVFP4
A ComfyUI-native quantized conversion of unsloth/Qwen3.8-27B-NVFP4
Unlike the core node, the custom node doesn’t run for `maxlength` steps and finishes within seconds_
<a href="https://huggingface.co/rzgar/Qwen3.8-27B-NVFP4-ComfyUI/resolve/main/workflow/screenshot.png" target="_blank"><img src="https://huggingface.co/rzgar/Qwen3.8-27B-NVFP4-ComfyUI/resolve/main/workflow/screenshot.png" width="1280" height="720" /></a>
File
Usage
Place the file in ComfyUI/models/text_encoders/ and load it with the LLM/text-encoder loader. Use with the Generate Text node.
Recommended: the "Generate Text (Qwen3.8)" custom node (install `ComfyUI-Qwen3.8-Text`)
The official Generate Text node for quantized checkpoints, it projects the output through
the embedding table instead of the real lmhead (untied), which produces incoherent text that **never stops and runs to `maxlength`**.
The custom node formats the prompt with the model's own chat template, uses the correct lm_head weights, and supports image and video inputs typical captions/answers finish in seconds.