Update README.md

README.md

@@ -46,6 +46,16 @@ tags:
 
     So, **1 + 1 = 2**. [end of text]
     ```
+5. If you have a GPU (RTX 4090 for example) with 24GB, you can offload 5 layers to the GPU for faster processing. If you have multiple GPUs, you can probably offload more layers.
+   ```bash
+   ./llama.cpp/llama-cli
+   --model unsloth/DeepSeek-V3-GGUF/DeepSeek-V3-Q2_K_XS/DeepSeek-V3-Q2_K_XS-00001-of-00005.gguf
+   --cache-type-k q5_0
+   --threads 16 
+   --prompt '<｜User｜>What is 1+1?<｜Assistant｜>'
+   --n-gpu-layers 5
+   ```
+6. Use `q4_0` KV cache for even faster workloads at the expense of some degraded accuracy.
 
 # Finetune Llama 3.3, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
 We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb