Update README.md

README.md

@@ -23,11 +23,11 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
 I use the following command line; adjust for your tastes and needs:
 
 ```
-./main -t 8 -ngl 32 -m EverythingLM-3B.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "prompt goes here"
+./main -t 8 -ngl 26 -m EverythingLM-3B.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "prompt goes here"
 ```
 Change `-t 8` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
 
-Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
+Change `-ngl 26` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
 
 If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`, also you can use --interactive-first to also start in interactive mode.