Update README.md

README.md

@@ -13,9 +13,11 @@ tags:
 
 # Model Card
 
-Dynamic quantization of DeepSeek-R1-0528 for **ik_llama** fork, optimized to run with 24GB to 32GB VRAM and 512GB RAM systems while providing the best balance between quality and performance for coding.
+Dynamic quantization of DeepSeek-R1-0528 using optimized format only available on **ik_llama** fork, resized to run with 24GB to 32GB VRAM and 512GB RAM systems while providing the best balance between quality and performance for coding.
 
-THIS QUANT ONLY RUNS ON THE **IK_LLAMA** FORK!!!
+THIS QUANT USES OPTIMIZED FORMAT THAT IS ONLY AVAILABLE ON **IK_LLAMA** FORK!!!
+
+Note that **ik_llama** can run all the **llama.cpp** quants, while adding support for interleaved formats (_R4 and _R8).
 
 See [this detailed guide](https://github.com/ikawrakow/ik_llama.cpp/discussions/258) on how to setup an run **ik_llama**.