ai-models/MiniMax-H3
2
0
Fork 0
mirror of https://www.modelscope.cn/Comfy-Org/MiniMax-H3.git synced 2026-08-30 22:32:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md (batch 1/1)

Browse Source
This commit is contained in:
systemd
2026-08-15 12:06:35 +00:00
parent 4f4df11786
commit bfc8546940
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -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`.
---