Update README.md

README.md

@@ -11,6 +11,22 @@ model-index:
   results: []
 ---
 
+Oh hell yeah here we go. I've never quanted a 32b model before so hopefully these turn out alright. I ended up making a few more quant types than usual to see about different tiers. Probably won't happen again.
+
+The advice in my [14b Kunou model](https://huggingface.co/Statuo/Qwen-2.5-14b-Kunou-EXL2-8bpw) quants probably still holds true here.
+
+[This is the 5bpw EXL2 quant of this model. For the original model, go here](https://huggingface.co/Sao10K/32B-Qwen2.5-Kunou-v1)
+<br>
+[For the 8bpw version, go here](https://huggingface.co/Statuo/Sao10k-Qwen2.5-32b-Kunou-EXL2-8bpw)
+<br>
+[For the 6bpw version, go here](https://huggingface.co/Statuo/Sao10k-Qwen2.5-32b-Kunou-EXL2-6bpw)
+<br>
+[For the 4.5bpw version, go here](https://huggingface.co/Statuo/Sao10k-Qwen2.5-32b-Kunou-EXL2-4.5bpw)
+<br>
+[For the 4bpw version, go here](https://huggingface.co/Statuo/Sao10k-Qwen2.5-32b-Kunou-EXL2-4bpw)
+
+---
+
 ![Kunou](https://huggingface.co/Sao10K/72B-Qwen2.5-Kunou-v1/resolve/main/knn.png)
 
 **Sister Versions for Lightweight Use!**