turboderp commited on
Commit
77ad33f
·
verified ·
1 Parent(s): c6d5162

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen3-VL-8B-Instruct
4
+ base_model_relation: quantized
5
+ quantized_by: turboderp
6
+ tags:
7
+ - exl3
8
+ ---
9
+
10
+ EXL3 quants of [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct)
11
+
12
+ ⚠️ Requires ExLlamaV3 v0.0.13 (or v0.0.12 `dev` branch)
13
+
14
+ [2.00 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/2.0bpw)
15
+ [2.25 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/2.25bpw)
16
+ [2.50 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/2.5bpw)
17
+ [3.00 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/3.0bpw)
18
+ [3.50 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/3.5bpw)
19
+ [4.00 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/4.0bpw)
20
+ [5.00 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/5.0bpw)
21
+ [6.00 bits per weight](https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/tree/6.0bpw)
22
+
23
+ <table>
24
+ <tr>
25
+ <td align="center">
26
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/2.0bpw.svg">
27
+ <img src="2.0bpw.svg" alt="2.00 bpw" width="160">
28
+ </a>
29
+ <div>2.00 bpw</div>
30
+ </td>
31
+ <td align="center">
32
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/2.25bpw.svg">
33
+ <img src="2.25bpw.svg" alt="2.25 bpw" width="160">
34
+ </a>
35
+ <div>2.25 bpw</div>
36
+ </td>
37
+ <td align="center">
38
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/2.5bpw.svg">
39
+ <img src="2.5bpw.svg" alt="2.5 bpw" width="160">
40
+ </a>
41
+ <div>2.5 bpw</div>
42
+ </td>
43
+ <td align="center">
44
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/3.0bpw.svg">
45
+ <img src="3.0bpw.svg" alt="3.00 bpw" width="160">
46
+ </a>
47
+ <div>3.00 bpw</div>
48
+ </td>
49
+ </tr>
50
+ <tr>
51
+ <td align="center">
52
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/3.5bpw.svg">
53
+ <img src="3.5bpw.svg" alt="3.50 bpw" width="160">
54
+ </a>
55
+ <div>3.50 bpw</div>
56
+ </td>
57
+ <td align="center">
58
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/4.0bpw.svg">
59
+ <img src="4.0bpw.svg" alt="4.00 bpw" width="160">
60
+ </a>
61
+ <div>4.00 bpw</div>
62
+ </td>
63
+ <td align="center">
64
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/5.0bpw.svg">
65
+ <img src="5.0bpw.svg" alt="5.00 bpw" width="160">
66
+ </a>
67
+ <div>5.00 bpw</div>
68
+ </td>
69
+ <td align="center">
70
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/6.0bpw.svg">
71
+ <img src="6.0bpw.svg" alt="6.00 bpw" width="160">
72
+ </a>
73
+ <div>6.00 bpw</div>
74
+ </td>
75
+ </tr>
76
+ <tr>
77
+ <td align="center">
78
+ <a href="https://huggingface.co/turboderp/Qwen3-VL-8B-Instruct-exl3/blob/main/api.svg">
79
+ <img src="api.svg" alt="API" width="160">
80
+ </a>
81
+ <div>API</div>
82
+ </td>
83
+ </tr>
84
+ </table>