Add files using upload-large-folder tool

README.md

@@ -11,10 +11,6 @@ pipeline_tag: text-generation
 
 # unsloth-Qwen3-Coder-30B-A3B-Instruct-qx6-mlx
 
-test model
-
-this is part of a series created to evaluate the effect of quanting with mixed precision
-
 This model [unsloth-Qwen3-Coder-30B-A3B-Instruct-qx6-mlx](https://huggingface.co/unsloth-Qwen3-Coder-30B-A3B-Instruct-qx6-mlx) was
 converted to MLX format from [unsloth/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct)
 using mlx-lm version **0.26.3**.

config.json

@@ -27,7 +27,7 @@
     "qkv_bias": false,
     "quantization": {
         "group_size": 64,
-        "bits": 4,
+        "bits": 6,
         "model.embed_tokens": {
             "group_size": 64,
             "bits": 6
@@ -1575,7 +1575,7 @@
     },
     "quantization_config": {
         "group_size": 64,
-        "bits": 4,
+        "bits": 6,
         "model.embed_tokens": {
             "group_size": 64,
             "bits": 6