Hi, sorry to bother you, I was looking for an email to contact you but I'm not very familiar here. I wanted to tell you that I am in love with your Utopia 13B model. He writes in a super way. But I have a problem. I have the utopia-13b.Q4_K_M.gguf model and use LM studio. The problem is that it is very slow to write. I have to set the Context Length to 1500 because 4096 blocks completely. Furthermore, GPU Layers I have to use it at 32. because 40 blocks.
Please, I can't do without this model. I've tried many but this is my favorite. Can you help me make it work better, faster? if you can write to me in my email [email protected]
Thank you ❤️ Claudio