Update README.md

README.md

@@ -33,13 +33,14 @@ tags:
 
 Our DeepSeek-V3-0324 GGUFs allow you to run the model in llama.cpp, LMStudio, Open WebUI and other inference frameworks.
 
-Includes 1.58-bit, 2-bit, 3-bit and 4-bit Dynamic versions, which yields better accuracy and results than standard quantization.
+Includes 1.78-bit, 2-bit, 3-bit and 4-bit Dynamic versions, which yields better accuracy and results than standard quantization.
 
 | MoE Bits | Type     | Disk Size   | Accuracy | Link                                                                                                       | Details                                           |
 |----------|----------|-------------|----------|------------------------------------------------------------------------------------------------------------|---------------------------------------------------|
-| 1.58bit (still uploading) | IQ1_S    | **131GB**   | Ok       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-IQ1_S)               | `down_proj` in MoE mixture of 2.06/1.56bit        |
-| 2.22bit (still uploading) | IQ2_XXS  | **183GB**   | Fair     | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-IQ2_XXS)             | `down_proj` in MoE all 2.06bit                    |
-| 2.51bit  | Q2_K_XL  | **212GB**   | Good     | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-Q2_K_XL)             | `down_proj` in MoE mixture of 3.5/2.5bit          |
+| 1.78bit (prelim) | IQ1_S    | **151GB**   | Ok       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-IQ1_S)               | `down_proj` in MoE mixture of 2.06/1.78bit        |
+| 1.93bit (prelim) | IQ1_M    | **178GB**   | Fair       | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-IQ1_M)               | `down_proj` in MoE mixture of 2.06/1.93bit        |
+| 2.42bit | IQ2_XXS  | **203GB**   | Better     | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-IQ2_XXS)             | `down_proj` in MoE all 2.42bit                    |
+| 2.71bit  | Q2_K_XL  | **232GB**   | Good     | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-Q2_K_XL)             | `down_proj` in MoE mixture of 3.5/2.71bit          |
 | 3.5bit   | Q3_K_XL  | **320GB**   | Great    | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-Q3_K_XL)             | `down_proj` in MoE mixture of 4.5/3.5bit          |
 | 4.5bit   | Q4_K_XL  | **406GB**   | Best     | [Link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF/tree/main/UD-Q4_K_XL)             | `down_proj` in MoE mixture of 5.5/4.5bit          |