Update README.md

README.md

@@ -10,16 +10,16 @@ tags:
 
 [Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next) optimized for MLX. Note: Uses MXFP4 for some module paths.
 
-**EDIT:** [v2](https://huggingface.co/spicyneuron/Qwen3-Next-Coder-MLX-mixed-4.5-bit/tree/v2) fixes some misassigned shared expert gates. Slower, but with 4x better perplexity.
+**EDIT:** [v2](https://huggingface.co/spicyneuron/Qwen3-Next-Coder-MLX-4.5bit/tree/v2) fixes some misassigned shared expert gates. Slower, but with 4x better perplexity.
 
-**EDIT:** [v3](https://huggingface.co/spicyneuron/Qwen3-Next-Coder-MLX-mixed-4.5-bit/tree/v3) bumps edge experts to Q8 for further perplexity improvement and minimal effect on speed.
+**EDIT:** [v3](https://huggingface.co/spicyneuron/Qwen3-Next-Coder-MLX-4.5bit/tree/v3) bumps edge experts to Q8 for further perplexity improvement and minimal effect on speed.
 
 # Usage
 
 ```sh
 # Start server at http://localhost:8080/v1/chat/completions
 uvx --from mlx-lm mlx_lm.server --host 127.0.0.1 --port 8080 \
-  --model spicyneuron/Qwen3-Next-Coder-MLX-mixed-4.5-bit
+  --model spicyneuron/Qwen3-Next-Coder-MLX-4.5bit
 ```
 
 # Methodology