Update README.md

README.md

@@ -9,8 +9,7 @@ EXL3 quants of [Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B)
 [4.00 bits per weight](https://huggingface.co/turboderp/Qwen3-30B-A3B-exl3/tree/4.0bpw)    
 [5.00 bits per weight](https://huggingface.co/turboderp/Qwen3-30B-A3B-exl3/tree/5.0bpw)    
 [6.00 bits per weight](https://huggingface.co/turboderp/Qwen3-30B-A3B-exl3/tree/6.0bpw)    
-
-While I work out a way to meaningfully measure perplexity for such a sparse model, here are some other tests:
+[8.00 bits per weight / H8](https://huggingface.co/turboderp/Qwen3-30B-A3B-exl3/tree/8.0bpw_H8)
 
 | Model    | HumanEval pass@1 | KL-div vs FP16 (wiki2 20k tokens) | Top-1 agreement vs FP16 |
 |----------|------------------|-----------------------------------|-------------------------|
@@ -19,4 +18,7 @@ While I work out a way to meaningfully measure perplexity for such a sparse mode
 | 4.00 bpw | 92.07%           | 0.0215                            | 94.33%                  |
 | 5.00 bpw | 93.29%           | 0.0094                            | 96.24%                  |
 | 6.00 bpw | 92.68%           | 0.0054                            | 97.45%                  |
-| FP16     | 91.46%           | -                                 | -                       |
+| 8.00 bpw | 91.46%           | 0.0020                            | 98.36%                  |
+| FP16     | 91.46%           | -                                 | -                       |
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/gvwDre0hFE9XUkatnP6Lp.png)