Hacker News new | ask | show | jobs
by lardo 1022 days ago
https://huggingface.co/TheBloke/CodeLlama-7B-GGUF describes codellama-7b.Q8_0.gguf as "very large, extremely low quality loss - not recommended"
1 comments

Q4_0 is often mentioned as being the "tried and true" quantization level to try first. I've heard folks have had good results with 3-bit quantization (Q3_K_M) as well
just tried it and its not good. I think one of the better feedback was asking for play an adventure in the style of Space Quest 1