Update README.md

README.md

@@ -21,9 +21,12 @@ datasets:
 
 Instructive model based on **Qwen-2.5-1.5B-Instruct**, trained on the Russian-language dataset **GrandMaster-PRO-MAX**. Designed for high-efficiency text processing in Russian and English, delivering precise responses and fast task execution.
 
-## GGUF
+## Quatized variants:
 
-- [Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF](https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF)
+- GGUF [Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF](https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF)
+- MLX
+  - 4 bit [Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_4bit](https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_4bit)
+  - 8 bit [Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_8bit](https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_8bit)
 
 ## Особенности: