Update README.md

README.md

@@ -48,6 +48,7 @@ Q2_K is undergoing PPL tests for one more update with a bit larger size (248.9 v
 | [DeepSeek-V3-0324-IQ4_XS.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-IQ4_XS) | IQ4_XS | 357.13GB | true | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 | [DeepSeek-V3-0324-Q3_K_XL.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q3_K_XL) | Q3_K_XL | 348.26GB | true | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
 | [DeepSeek-V3-0324-Q3_K_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q3_K_M) | Q3_K_M | 319.20GB | true | Low quality. |
+| [DeepSeek-V3-0324-IQ3_XXS-V2.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-IQ3_XXS-V2) | IQ3_XXS | 261.74GB | true | Attempted to modify tensor quant levels for better performance. |
 | [DeepSeek-V3-0324-IQ3_XXS.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-IQ3_XXS) | IQ3_XXS | 257.93GB | true | Lower quality, new method with decent performance, comparable to Q3 quants. |
 | [DeepSeek-V3-0324-Q2_K_L-V2.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q2_K_L-V2) | Q2_K_L | 247.35GB | true | Attempted to modify tensor quant levels for better performance. Also uses Q8_0 for embed and output weights. |
 | [DeepSeek-V3-0324-Q2_K_L.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q2_K_L) | Q2_K_L | 244.93GB | true | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |