Update README.md

README.md

@@ -14,7 +14,7 @@ This model [mlx-community/LongCat-Flash-Chat-mlx-DQ6_K_M](https://huggingface.co
 converted to MLX format from [meituan-longcat/LongCat-Flash-Chat](https://huggingface.co/meituan-longcat/LongCat-Flash-Chat)
 using mlx-lm version **0.28.1**.
 
-This is created for people using a single Apple Mac Studio M3 Ultra with 512 GB. The 4-bit version of Ring 1T does not fit. Using research results, we aim to get 4-bit performance from a slightly smaller and smarter quantization. It should also not be so large that it leaves no memory for a useful context window.
+This is created for people using a single Apple Mac Studio M3 Ultra with 512 GB. The 8-bit version of Ring 1T does not fit. Using research results, we aim to get almost-8bit performance from a slightly smaller and smarter quantization. It should also not be so large that it leaves no memory for a useful context window.
 
 ```bash
 pip install mlx-lm
@@ -24,7 +24,7 @@ mlx_lm.generate --model mlx-community/LongCat-Flash-Chat-mlx-DQ6_K_M --temp 0.7
 
 ---
 
-## What is the DQ3_K_M quant about?
+## What is the DQ6_K_M quant about? It comes from a paper on DQ3_K_M
 
 In the Arxiv paper [Quantitative Analysis of Performance Drop in DeepSeek Model Quantization](https://arxiv.org/abs/2505.02390) the authors write,
 
@@ -38,7 +38,7 @@ The resulting multi-bitwidth quantization has been well tested and documented.
 
 ---
 
-## How can you create your own DQ3_K_M quants?
+## How can you create your own DQ6_K_M quants?
 
 In the `convert.py` file of mlx-lm on your system ( [you can see the original code here](https://github.com/ml-explore/mlx-lm/blob/main/mlx_lm/convert.py) ), replace the code inside `def mixed_quant_predicate()` with something like