Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen3-8B-Q2_K.gguf +3 -0
- Qwen3-8B-Q3_K_L.gguf +3 -0
- Qwen3-8B-Q3_K_M.gguf +3 -0
- Qwen3-8B-Q3_K_S.gguf +3 -0
- Qwen3-8B-Q4_0.gguf +3 -0
- Qwen3-8B-Q4_K_M.gguf +3 -0
- Qwen3-8B-Q4_K_S.gguf +3 -0
- Qwen3-8B-Q5_0.gguf +3 -0
- Qwen3-8B-Q5_K_M.gguf +3 -0
- Qwen3-8B-Q5_K_S.gguf +3 -0
- Qwen3-8B-Q6_K.gguf +3 -0
- Qwen3-8B-Q8_0.gguf +3 -0
- README.md +119 -0
.gitattributes
CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Qwen3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen3-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen3-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen3-8B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d25f5bae7bab08c38b709840193dba941e79baa19dd3ed12c4848de5b0765d6f
|
3 |
+
size 3281732800
|
Qwen3-8B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30fe0f29261d32f54a5d4acd94752c30677a474d25f32989ae1e1f9653026eff
|
3 |
+
size 4431393984
|
Qwen3-8B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c0cdf874dd1fa7ab4840d31840ed627b91caae1ca3154b6257f3f350c66d14a
|
3 |
+
size 4124161216
|
Qwen3-8B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71a5fcfcc268731e341ad40e3900fc75058a170728572d5266d5a7f7349497c0
|
3 |
+
size 3769611456
|
Qwen3-8B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9db3caf44a519c45e5dc7ca37c3dcf1720d9cc9c9da332d139984ad197c988d8
|
3 |
+
size 4774749376
|
Qwen3-8B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6428709fa7cb52e83ce95b052e5edd7ab2d6837c6dc5c1d4dbafc467398d5cf5
|
3 |
+
size 5027783872
|
Qwen3-8B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4d05451feb788a65917af5cca7c9e98808b91cfccb2ca7b175754205cce7ebb
|
3 |
+
size 4802012352
|
Qwen3-8B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0983251f3085b45055c39cffac7d4b0e2e311195672c830e24d88c0a9c3eda6
|
3 |
+
size 5720761536
|
Qwen3-8B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23bfdcb5285fdff750b3fb7eb675b34e62ad917f350a22307ba02dcb76bbf5b7
|
3 |
+
size 5851112640
|
Qwen3-8B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98c3e5df4c0568a5486af5575b6ccdabda2136558cf182267da513c025d59322
|
3 |
+
size 5720761536
|
Qwen3-8B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd5f35fd5c9196efa2ff2fe9d417f4ee7f78ac11b4e275789db27da21a2e701b
|
3 |
+
size 6725899456
|
Qwen3-8B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84ea94311add32ac6c562afd9250bc3228f8eff5f504694899f201031b01be3d
|
3 |
+
size 8709518528
|
README.md
ADDED
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
base_model: Qwen/Qwen3-8B
|
7 |
+
tags:
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
---
|
11 |
+
|
12 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
13 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
14 |
+
</div>
|
15 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
16 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
17 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
18 |
+
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
|
19 |
+
</p>
|
20 |
+
</div>
|
21 |
+
</div>
|
22 |
+
|
23 |
+
## Qwen/Qwen3-8B - GGUF
|
24 |
+
|
25 |
+
This repo contains GGUF format model files for [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B).
|
26 |
+
|
27 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5214](https://github.com/ggml-org/llama.cpp/commit/eaea3253244dc4bbe07f6cd81325847ccc6cf93e).
|
28 |
+
|
29 |
+
## Our projects
|
30 |
+
<table border="1" cellspacing="0" cellpadding="10">
|
31 |
+
<tr>
|
32 |
+
<th style="font-size: 25px;">Awesome MCP Servers</th>
|
33 |
+
<th style="font-size: 25px;">TensorBlock Studio</th>
|
34 |
+
</tr>
|
35 |
+
<tr>
|
36 |
+
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
|
37 |
+
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
|
38 |
+
</tr>
|
39 |
+
<tr>
|
40 |
+
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
|
41 |
+
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
|
42 |
+
</tr>
|
43 |
+
<tr>
|
44 |
+
<th>
|
45 |
+
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
|
46 |
+
display: inline-block;
|
47 |
+
padding: 8px 16px;
|
48 |
+
background-color: #FF7F50;
|
49 |
+
color: white;
|
50 |
+
text-decoration: none;
|
51 |
+
border-radius: 6px;
|
52 |
+
font-weight: bold;
|
53 |
+
font-family: sans-serif;
|
54 |
+
">π See what we built π</a>
|
55 |
+
</th>
|
56 |
+
<th>
|
57 |
+
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
|
58 |
+
display: inline-block;
|
59 |
+
padding: 8px 16px;
|
60 |
+
background-color: #FF7F50;
|
61 |
+
color: white;
|
62 |
+
text-decoration: none;
|
63 |
+
border-radius: 6px;
|
64 |
+
font-weight: bold;
|
65 |
+
font-family: sans-serif;
|
66 |
+
">π See what we built π</a>
|
67 |
+
</th>
|
68 |
+
</tr>
|
69 |
+
</table>
|
70 |
+
|
71 |
+
## Prompt template
|
72 |
+
|
73 |
+
```
|
74 |
+
<|im_start|>system
|
75 |
+
{system_prompt}<|im_end|>
|
76 |
+
<|im_start|>user
|
77 |
+
{prompt}<|im_end|>
|
78 |
+
<|im_start|>assistant
|
79 |
+
```
|
80 |
+
|
81 |
+
## Model file specification
|
82 |
+
|
83 |
+
| Filename | Quant type | File Size | Description |
|
84 |
+
| -------- | ---------- | --------- | ----------- |
|
85 |
+
| [Qwen3-8B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q2_K.gguf) | Q2_K | 3.282 GB | smallest, significant quality loss - not recommended for most purposes |
|
86 |
+
| [Qwen3-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q3_K_S.gguf) | Q3_K_S | 3.770 GB | very small, high quality loss |
|
87 |
+
| [Qwen3-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q3_K_M.gguf) | Q3_K_M | 4.124 GB | very small, high quality loss |
|
88 |
+
| [Qwen3-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q3_K_L.gguf) | Q3_K_L | 4.431 GB | small, substantial quality loss |
|
89 |
+
| [Qwen3-8B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q4_0.gguf) | Q4_0 | 4.775 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
90 |
+
| [Qwen3-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q4_K_S.gguf) | Q4_K_S | 4.802 GB | small, greater quality loss |
|
91 |
+
| [Qwen3-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q4_K_M.gguf) | Q4_K_M | 5.028 GB | medium, balanced quality - recommended |
|
92 |
+
| [Qwen3-8B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q5_0.gguf) | Q5_0 | 5.721 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
93 |
+
| [Qwen3-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q5_K_S.gguf) | Q5_K_S | 5.721 GB | large, low quality loss - recommended |
|
94 |
+
| [Qwen3-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q5_K_M.gguf) | Q5_K_M | 5.851 GB | large, very low quality loss - recommended |
|
95 |
+
| [Qwen3-8B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q6_K.gguf) | Q6_K | 6.726 GB | very large, extremely low quality loss |
|
96 |
+
| [Qwen3-8B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-8B-GGUF/blob/main/Qwen3-8B-Q8_0.gguf) | Q8_0 | 8.710 GB | very large, extremely low quality loss - not recommended |
|
97 |
+
|
98 |
+
|
99 |
+
## Downloading instruction
|
100 |
+
|
101 |
+
### Command line
|
102 |
+
|
103 |
+
Firstly, install Huggingface Client
|
104 |
+
|
105 |
+
```shell
|
106 |
+
pip install -U "huggingface_hub[cli]"
|
107 |
+
```
|
108 |
+
|
109 |
+
Then, downoad the individual model file the a local directory
|
110 |
+
|
111 |
+
```shell
|
112 |
+
huggingface-cli download tensorblock/Qwen_Qwen3-8B-GGUF --include "Qwen3-8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
113 |
+
```
|
114 |
+
|
115 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
116 |
+
|
117 |
+
```shell
|
118 |
+
huggingface-cli download tensorblock/Qwen_Qwen3-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
119 |
+
```
|