-
Notifications
You must be signed in to change notification settings - Fork 117
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
How much RAM needed ? #146
Comments
Currently, you may need some swap memory. We are currently trying to develop a smaller model to meet the low memory limit (30GB) |
Thanks for the reply, even with swap memory it crashes. I will wait patiently |
Thank you, we will hurry up. |
Thank you @bubbliiiing, you are looking into possibility of reducing the memory requirements. It would be helpful if you can provide fp8, quantized or GGUF model (not sure if possible for this). I have seen the requirement for some tools was 4xH100 for inference now running on consumer GPU's with as low as 12 GB VRAM. 1 such example is |
30GB RAM will be support in #154 |
Hi, i have 32 gb RAM, and a 4060 ti 16g, I cant load the model, my ram is at 100%, and takes too long, is it "normal" ? must I have more Ram ?
The text was updated successfully, but these errors were encountered: