turboderp commited on
Commit
fea63fc
·
verified ·
1 Parent(s): b04bca8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -3
README.md CHANGED
@@ -1,3 +1,17 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+
5
+ EXL3 quants of [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)
6
+
7
+ [2.75 bits per weight / H5](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/2.5bpw) *
8
+ [3.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/3.0bpw) *
9
+ [3.50 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/3.5bpw)
10
+ [4.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/4.0bpw)
11
+ [5.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/5.0bpw)
12
+ [6.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/6.0bpw)
13
+ [8.00 bits per weight / H8](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/8.0bpw_H8)
14
+
15
+ *) Reasoning seems unstable below 3.5 bpw
16
+
17
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/UQ9YuDyEPFMfBb2beXcS8.png)