Update README.md

README.md

@@ -20,5 +20,10 @@ Using llama.cpp fork: [https://github.com/fairydreaming/llama.cpp/tree/deepseek-
 - Merged GGUF should appear
 
 # Quants:
-- bf16
-- q8_0
+- bf16 (generating, 85% complete)
+- f16 (after q4_k_m, but just use bf16)
+- f32 (may require some time to upload, after q8_0)
+- q8_0 (after bf16)
+- q4_k_m (after q8_0)
+
+If quantize.exe supports it I will make RTN quants.