Update README.md

README.md

@@ -85,6 +85,19 @@ out_dtype: float16
 3. **Ethical Research and Dialogue:** Ideal for controlled environments where researchers can test response ethics, alignment, and safety controls.
 4. **General Instruction-Following:** Useful in assistant-like roles for answering questions, following system prompts, or generating informative content with flexible degrees of guidance.
 
+---
+
+### Quantized Versions
+
+For users looking to leverage optimized quantized versions of this model, we are grateful to **MrRaderMacher** for providing GGUF quantizations. These versions are accessible through the links below:
+
+- **Static quants**: Available at [huggingface.co/mradermacher/Llama-3-Aetheric-Hermes-Lexi-Smaug-8B-GGUF](https://huggingface.co/mradermacher/Llama-3-Aetheric-Hermes-Lexi-Smaug-8B-GGUF)
+- **Weighted/imatrix quants**: Available at [huggingface.co/mradermacher/Llama-3-Aetheric-Hermes-Lexi-Smaug-8B-i1-GGUF](https://huggingface.co/mradermacher/Llama-3-Aetheric-Hermes-Lexi-Smaug-8B-i1-GGUF)
+
+We recommend users select the **imatrix version** for the best inference performance, as it provides an optimal balance of efficiency and accuracy. Once again, a heartfelt thanks to **MrRaderMacher** for his contributions to the community with these quantized versions.
+
+---
+
 ### Example Usage
 
 This model has unique Stop Strings, for optimal inference in LM Studio, enter the following setting under Prompt Format > Stop Strings: