Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Why Wan2.1-T2V-14B can not run with one RXT 4090 24GB card? #97

Open
WechatOfficalAccount-Streamlit opened this issue Feb 27, 2025 · 2 comments

Comments

@WechatOfficalAccount-Streamlit
Copy link

WechatOfficalAccount-Streamlit commented Feb 27, 2025

For other 14B LLM model such as Qwen/Qwen2.5-14B-Instruct, can run with one RXT 4090 24GB card normally
Why Wan2.1-T2V-14B can not run with one RXT 4090 24GB card?
because its safetensors files more bigger?

@JackChius
Copy link

you may run in fp8 version
fp8:
https://www.modelscope.cn/models/Kijai/WanVideo_comfy/files

@jinqiupeter
Copy link

You can with this PR (if you don't want to use ComfyUI) #80

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants