Update README.md

README.md

@@ -41,6 +41,7 @@ Q2_K is undergoing PPL tests for one more update with a bit larger size (248.9 v
 | [DeepSeek-V3-0324-Q5_K_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q5_K_M) | Q5_K_M | 475.40GB | true | High quality, *recommended*. |
 | [DeepSeek-V3-0324-Q5_K_S.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q5_K_S) | Q5_K_S | 461.81GB | true | High quality, *recommended*. |
 | [DeepSeek-V3-0324-Q4_1.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q4_1) | Q4_1 | 419.94GB | true | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [DeepSeek-V3-0324-Q4_K_M-V2.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q4_K_M-V2) | Q4_K_M | 406.99GB | true | Attempted to modify tensor quant levels for better performance. *recommended* |
 | [DeepSeek-V3-0324-Q4_K_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q4_K_M) | Q4_K_M | 404.43GB | true | Good quality, default size for most use cases, *recommended*. |
 | [DeepSeek-V3-0324-Q4_K_S.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q4_K_S) | Q4_K_S | 380.00GB | true | Slightly lower quality with more space savings, *recommended*. |
 | [DeepSeek-V3-0324-Q4_0.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-V3-0324-GGUF/tree/main/deepseek-ai_DeepSeek-V3-0324-Q4_0) | Q4_0 | 379.03GB | true | Legacy format, offers online repacking for ARM and AVX CPU inference. |