Update README.md

README.md

@@ -23,7 +23,7 @@ The idea is that these models perform very well in their respective fields, and
 | [Q5_K_M](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q5_k_m.gguf) | Q5_K_M | 5 | ~16.6 GB| ~18.6 GB | large, balanced quality - recommended |
 | [Q6 XL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q6_k.gguf) | Q6_K | 6 | 19.8 GB| 21.8 GB | very large, extremely low quality loss |
 | [Q8 XXL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q8_0.gguf) | Q8_0 | 8 | 25.7 GB| 27.7 GB | very large, extremely low quality loss - not recommended |
-| [f16 XXXL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-f16.gguf) | f16 | 8 | 48.3 GB| 50.3 GB | very VERY large, extremely low quality loss - not recommended |
+| [f16 XXXL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-f16.gguf) | f16 | 8 | 48.3 GB| 50.3 GB | very VERY large, nearly lossless - not recommended |
 # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)"
 ### (from the MistralAI papers...click the quoted question above to navigate to it directly.)