Update README.md

README.md

@@ -64,11 +64,26 @@ and
 
 These two models are stuffed into one MASSSIVE 51B merge that is stronger in performance and understanding than both donor models.
 
+---
+
+<B>QUANTS:</b>
+
+---
+
+Special Thanks to Team Mradermacher for the quants:
+
+GGUF:
+
+https://huggingface.co/mradermacher/Qwen2.5-Godzilla-Coder-51B-128k-GGUF
+
+GGUF-IMATRIX:
+
+https://huggingface.co/mradermacher/Qwen2.5-Godzilla-Coder-51B-128k-i1-GGUF
+
 Test quants are here:
 
 [ https://huggingface.co/DavidAU/Qwen2.5-Godzilla-Coder-51B-gguf ] 
 
-(full quants coming shortly...)
 
 CONFIGS:
 - #1 -> Qwen2.5-Coder-32B-Instruct primary/start, with OlympicCoder-32B as "finalizer". (this REPO)