Hugging Face's logo

second-state
/
Qwen3-32B-GGUF

GGUF
qwen3
conversational
Model card Files Community
2
apepkuss79 commited on
Commit
35f8462
·
verified ·
1 Parent(s): aef9e25

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -64
README.md CHANGED
@@ -1,65 +1,65 @@
1
- ---
2
- base_model: Qwen/Qwen3-32B
3
- license: other
4
- license_name: qwen-research
5
- license_link: https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE
6
- model_creator: Qwen
7
- model_name: Qwen3-32B
8
- quantized_by: Second State Inc.
9
- ---
10
-
11
- <!-- header start -->
12
- <!-- 200823 -->
13
- <div style="width: auto; margin-left: auto; margin-right: auto">
14
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
- </div>
16
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
17
- <!-- header end -->
18
-
19
- # Qwen3-32B-GGUF
20
-
21
- ## Original Model
22
-
23
- [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)
24
-
25
- ## Run with LlamaEdge
26
-
27
- - LlamaEdge version: coming soon
28
-
29
- <!-- - LlamaEdge version: [v0.16.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.8) -->
30
-
31
- - Prompt template
32
-
33
- - Prompt type: `chatml`
34
-
35
- - Context size: `128000`
36
-
37
- - Run as LlamaEdge service
38
-
39
- ```bash
40
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-32B-Q5_K_M.gguf \
41
- llama-api-server.wasm \
42
- --model-name Qwen3-32B \
43
- --prompt-template chatml \
44
- --ctx-size 128000
45
- ```
46
-
47
- <!-- ## Quantized GGUF Models
48
-
49
- | Name | Quant method | Bits | Size | Use case |
50
- | ---- | ---- | ---- | ---- | ----- |
51
- | [Qwen3-32B-Q2_K.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q2_K.gguf) | Q2_K | 2 | 3.28 GB| smallest, significant quality loss - not recommended for most purposes |
52
- | [Qwen3-32B-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.43 GB| small, substantial quality loss |
53
- | [Qwen3-32B-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.12 GB| very small, high quality loss |
54
- | [Qwen3-32B-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.77 GB| very small, high quality loss |
55
- | [Qwen3-32B-Q4_0.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q4_0.gguf) | Q4_0 | 4 | 4.77 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
56
- | [Qwen3-32B-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q4_K_M.gguf) | Q4_K_M | 4 | 5.03 GB| medium, balanced quality - recommended |
57
- | [Qwen3-32B-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.80 GB| small, greater quality loss |
58
- | [Qwen3-32B-Q5_0.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q5_0.gguf) | Q5_0 | 5 | 5.72 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
59
- | [Qwen3-32B-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.85 GB| large, very low quality loss - recommended |
60
- | [Qwen3-32B-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.72 GB| large, low quality loss - recommended |
61
- | [Qwen3-32B-Q6_K.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q6_K.gguf) | Q6_K | 6 | 6.73 GB| very large, extremely low quality loss |
62
- | [Qwen3-32B-Q8_0.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q8_0.gguf) | Q8_0 | 8 | 8.71 GB| very large, extremely low quality loss - not recommended |
63
- | [Qwen3-32B-f16.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-f16.gguf) | f16 | 16 | 16.4 GB| | -->
64
-
65
  *Quantized with llama.cpp b5097*
 
1
+ ---
2
+ base_model: Qwen/Qwen3-32B
3
+ license: other
4
+ license_name: qwen-research
5
+ license_link: https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE
6
+ model_creator: Qwen
7
+ model_name: Qwen3-32B
8
+ quantized_by: Second State Inc.
9
+ ---
10
+
11
+ <!-- header start -->
12
+ <!-- 200823 -->
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
17
+ <!-- header end -->
18
+
19
+ # Qwen3-32B-GGUF
20
+
21
+ ## Original Model
22
+
23
+ [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)
24
+
25
+ ## Run with LlamaEdge
26
+
27
+ <!-- - LlamaEdge version: coming soon -->
28
+
29
+ - LlamaEdge version: [v0.17.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.17.0) and above
30
+
31
+ - Prompt template
32
+
33
+ - Prompt type: `chatml`
34
+
35
+ - Context size: `128000`
36
+
37
+ - Run as LlamaEdge service
38
+
39
+ ```bash
40
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-32B-Q5_K_M.gguf \
41
+ llama-api-server.wasm \
42
+ --model-name Qwen3-32B \
43
+ --prompt-template chatml \
44
+ --ctx-size 128000
45
+ ```
46
+
47
+ <!-- ## Quantized GGUF Models
48
+
49
+ | Name | Quant method | Bits | Size | Use case |
50
+ | ---- | ---- | ---- | ---- | ----- |
51
+ | [Qwen3-32B-Q2_K.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q2_K.gguf) | Q2_K | 2 | 3.28 GB| smallest, significant quality loss - not recommended for most purposes |
52
+ | [Qwen3-32B-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.43 GB| small, substantial quality loss |
53
+ | [Qwen3-32B-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.12 GB| very small, high quality loss |
54
+ | [Qwen3-32B-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.77 GB| very small, high quality loss |
55
+ | [Qwen3-32B-Q4_0.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q4_0.gguf) | Q4_0 | 4 | 4.77 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
56
+ | [Qwen3-32B-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q4_K_M.gguf) | Q4_K_M | 4 | 5.03 GB| medium, balanced quality - recommended |
57
+ | [Qwen3-32B-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.80 GB| small, greater quality loss |
58
+ | [Qwen3-32B-Q5_0.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q5_0.gguf) | Q5_0 | 5 | 5.72 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
59
+ | [Qwen3-32B-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.85 GB| large, very low quality loss - recommended |
60
+ | [Qwen3-32B-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.72 GB| large, low quality loss - recommended |
61
+ | [Qwen3-32B-Q6_K.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q6_K.gguf) | Q6_K | 6 | 6.73 GB| very large, extremely low quality loss |
62
+ | [Qwen3-32B-Q8_0.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-Q8_0.gguf) | Q8_0 | 8 | 8.71 GB| very large, extremely low quality loss - not recommended |
63
+ | [Qwen3-32B-f16.gguf](https://huggingface.co/second-state/Qwen3-32B-GGUF/blob/main/Qwen3-32B-f16.gguf) | f16 | 16 | 16.4 GB| | -->
64
+
65
  *Quantized with llama.cpp b5097*