Update README.md

README.md

@@ -38,14 +38,14 @@ Our DeepSeek-V3-0324 GGUFs allow you to run the model in llama.cpp, LMStudio, Op
 
 Includes 1-4-bit Dynamic versions, which yields better accuracy and results than standard quantization.
 
-| MoE Bits | Type     | Disk Size    | Link                                                                                                       | Details                                           |
-|----------|----------|-------------|----------|------------------------------------------------------------------------------------------------------------|---------------------------------------------------|
-| 1.78bit (prelim) | IQ1_S    | **192B**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-IQ1_S)               | `down_proj` in MoE mixture of 2.06/1.78bit        |
-| 1.93bit (prelim) | IQ1_M    | **200GB**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-IQ1_M)               | `down_proj` in MoE mixture of 2.06/1.93bit        |
-| 2.42bit | IQ2_XXS  | **215GB**    | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-IQ2_XXS)             | `down_proj` in MoE all 2.42bit                    |
-| 2.71bit  | Q2_K_XL  | **250GB**     | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-Q2_K_XL)             | `down_proj` in MoE mixture of 3.5/2.71bit          |
-| 3.5bit   | Q3_K_XL  | **296GB**   | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-Q3_K_XL)             | `down_proj` in MoE mixture of 4.5/3.5bit          |
-| 4.5bit   | Q4_K_XL  | **384GB**    | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-Q4_K_XL)             | `down_proj` in MoE mixture of 5.5/4.5bit          |
+| **MoE Bits**       | **Type**   | **Disk Size** | **Link**                                                                                                                                     | **Details**                                 |
+|--------------------|------------|----------------|----------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------|
+| 1.78bit (prelim)   | IQ1_S      | **192GB**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-IQ1_S)                                                           | down_proj in MoE mixture of 2.06/1.78bit     |
+| 1.93bit (prelim)   | IQ1_M      | **200GB**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-IQ1_M)                                                           | down_proj in MoE mixture of 2.06/1.93bit     |
+| 2.42bit            | IQ2_XXS    | **215GB**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-IQ2_XXS)                                                         | down_proj in MoE all 2.42bit                 |
+| 2.71bit            | Q2_K_XL    | **250GB**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-Q2_K_XL)                                                         | down_proj in MoE mixture of 3.5/2.71bit      |
+| 3.5bit             | Q3_K_XL    | **296GB**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-Q3_K_XL)                                                         | down_proj in MoE mixture of 4.5/3.5bit       |
+| 4.5bit             | Q4_K_XL    | **384GB**       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD/tree/main/UD-Q4_K_XL)                                                         | down_proj in MoE mixture of 5.5/4.5bit       |
 
 Prelim = preliminary - through our testing, they're generally fine but sometimes don't produce the best code and so more work/testing needs to be done.
 2.71bit was found to be the best in terms of performance/size and produces code that is great and works well. 2.42bit was also found to pass all our tests.