From 4f4df117860db743c827262ce0f98de4836d6460 Mon Sep 17 00:00:00 2001
From: systemd <systemd@163.com>
Date: Sun, 9 Aug 2026 12:06:22 +0000
Subject: [PATCH] Update README.md (batch 1/1)

---
 README.md | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/README.md b/README.md
index ac2ff27..92c1b1d 100644
--- a/README.md
+++ b/README.md
@@ -15,6 +15,16 @@ Repackaged model files for ComfyUI.
 
 Original model repository: https://huggingface.co/MiniMaxAI/MiniMax-H3
 
+The Qwen3-VL-32B nvfp4_awq quant is converted from: https://huggingface.co/cybermotaz/Qwen3-VL-32B-Instruct-NVFP4
+
+- This nvfp4 text encoder does not require Blackwell GPU to use.
+
+- For diffusion_model prefer int8_convrot if you are able to use pytorch with cu130.
+
+- Fp8_scaled should only be used if you for any reason can not use the int8_convrot.
+
+---
+
 Place the files in the following folders:
 
 ```