From bfc8546940b6bdd7ba87f57b3e6e7f021d9b4d90 Mon Sep 17 00:00:00 2001 From: systemd Date: Sat, 15 Aug 2026 12:06:35 +0000 Subject: [PATCH] Update README.md (batch 1/1) --- README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 92c1b1d..5a13031 100644 --- a/README.md +++ b/README.md @@ -15,13 +15,13 @@ 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 +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. +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. +For diffusion models 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. +`fp8_scaled` should only be used if you cannot use `int8_convrot`. ---