spicyneuron
/

Qwen3-Next-Coder-MLX-mixed-4.5-bit

Text Generation

4-bit precision

Model card Files Files and versions

spicyneuron commited on 6 days ago

Commit

7b1a697

·

verified ·

1 Parent(s): b3bf7d0

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ tags:
 [Qwen3-Coder-Next](https://huggingface.co/moonshotai/Qwen/Qwen3-Coder-Next) optimized for MLX. Note: Uses MXFP4 for some module paths.
-**EDIT:** v2 fixes some misassigned shared expert gates. Slower, but with 4x better perplexity. (recommended)
 **EDIT:** v3 bumps edge experts to Q8 for further perplexity improvement and minimal effect on speed.

 [Qwen3-Coder-Next](https://huggingface.co/moonshotai/Qwen/Qwen3-Coder-Next) optimized for MLX. Note: Uses MXFP4 for some module paths.
+**EDIT:** v2 fixes some misassigned shared expert gates. Slower, but with 4x better perplexity.
 **EDIT:** v3 bumps edge experts to Q8 for further perplexity improvement and minimal effect on speed.