Hugging Face's logo

bartowski
/
Qwen1.5-32B-Chat-GGUF

Text Generation
GGUF
English
chat
Model card Files Community
bartowski commited on
Commit
369aa45
•
1 Parent(s): d549822

Llamacpp quants

Browse files
Files changed (21) hide show
  1. .gitattributes +18 -0
  2. Qwen1.5-32B-Chat-IQ3_M.gguf +3 -0
  3. Qwen1.5-32B-Chat-IQ3_S.gguf +3 -0
  4. Qwen1.5-32B-Chat-IQ4_NL.gguf +3 -0
  5. Qwen1.5-32B-Chat-IQ4_XS.gguf +3 -0
  6. Qwen1.5-32B-Chat-Q2_K.gguf +3 -0
  7. Qwen1.5-32B-Chat-Q3_K_L.gguf +3 -0
  8. Qwen1.5-32B-Chat-Q3_K_M.gguf +3 -0
  9. Qwen1.5-32B-Chat-Q3_K_S.gguf +3 -0
  10. Qwen1.5-32B-Chat-Q4_0.gguf +3 -0
  11. Qwen1.5-32B-Chat-Q4_K_M.gguf +3 -0
  12. Qwen1.5-32B-Chat-Q4_K_S.gguf +3 -0
  13. Qwen1.5-32B-Chat-Q5_0.gguf +3 -0
  14. Qwen1.5-32B-Chat-Q5_K_M.gguf +3 -0
  15. Qwen1.5-32B-Chat-Q5_K_S.gguf +3 -0
  16. Qwen1.5-32B-Chat-Q6_K.gguf +3 -0
  17. Qwen1.5-32B-Chat-Q8_0.gguf +3 -0
  18. Qwen1.5-32B-Chat-fp16.gguf/Qwen1.5-32B-Chat-fp16_part_a +3 -0
  19. Qwen1.5-32B-Chat-fp16.gguf/Qwen1.5-32B-Chat-fp16_part_b +3 -0
  20. Qwen1.5-32B-Chat-fp16.gguf/combine.sh +2 -0
  21. README.md +41 -0
.gitattributes CHANGED
@@ -33,3 +33,21 @@ 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
+ Qwen1.5-32B-Chat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen1.5-32B-Chat-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen1.5-32B-Chat-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen1.5-32B-Chat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen1.5-32B-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen1.5-32B-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen1.5-32B-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen1.5-32B-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen1.5-32B-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen1.5-32B-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen1.5-32B-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen1.5-32B-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Qwen1.5-32B-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Qwen1.5-32B-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Qwen1.5-32B-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Qwen1.5-32B-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Qwen1.5-32B-Chat-fp16.gguf/Qwen1.5-32B-Chat-fp16_part_a filter=lfs diff=lfs merge=lfs -text
53
+ Qwen1.5-32B-Chat-fp16.gguf/Qwen1.5-32B-Chat-fp16_part_b filter=lfs diff=lfs merge=lfs -text
Qwen1.5-32B-Chat-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b30961cacb4f30846dc5957d830136615a1cb45a319943bb59e1c14c49ffbe
3
+ size 14700592800
Qwen1.5-32B-Chat-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9dfd3d1281260a5c6a6bcd77dce67540a7c6df8052061b9e7d24cefa3099e5
3
+ size 14328757920
Qwen1.5-32B-Chat-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1afcd94ee452aa850b150ac1408b540b67fa6f305f7bdc6a80eaad658520c9
3
+ size 18680860320
Qwen1.5-32B-Chat-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb9ce641909752c1c33c06e443c3daae683abc318ffa40d4848dae6ff4baeee
3
+ size 17734766240
Qwen1.5-32B-Chat-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be634e2a268e5e5c64851d32db65ff6b524b87d7d3621e97283049f2e971075f
3
+ size 12222000800
Qwen1.5-32B-Chat-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ce60fd363a6b0b36009936f1f9360760f4b1c301b9e893b45751ec1e03ecb0
3
+ size 17117314720
Qwen1.5-32B-Chat-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a2215a7acb4771fb395bff6f791aa242530d66e9be341fd5b7e0d584977a1c
3
+ size 15815114400
Qwen1.5-32B-Chat-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22bcb20591e19ec34b6525abf2427c94e08e1093a4806f3f149094f92af62516
3
+ size 14284193440
Qwen1.5-32B-Chat-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d48c4f7279bc9580847c74a90c59a5a583ef084bd81ce58ba49c4c2cbdc773ec
3
+ size 18498670240
Qwen1.5-32B-Chat-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61abbdd83bfbece3bb8100f1f2dee5df94b397497cc33decb2a403d27c21c3b
3
+ size 19698962080
Qwen1.5-32B-Chat-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5f9b2e36830142cf8a4a8eed0a3e05e224ef40f04c2d0048a44c0a1acc1268
3
+ size 18641538720
Qwen1.5-32B-Chat-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05dbba137e2910e62e3a7b5ebb4b1aeffcc7cd9760f50255c3bbaf7f040fd44b
3
+ size 22465236640
Qwen1.5-32B-Chat-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e7d7ce346a9babc55a37ffbc465c3f1cc8ff6909c0d55c19d535a0779cd09f
3
+ size 23083568800
Qwen1.5-32B-Chat-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53fd5d507da12d5e610b6fda480f15f3f126932ec91606bc774d73dc81a94025
3
+ size 22465236640
Qwen1.5-32B-Chat-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0824cf65ce277acd948dd550dd780f75d61322945820fc9966988433474eaca2
3
+ size 26679713440
Qwen1.5-32B-Chat-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91528a62aa83dd5c10761e46728e4dc9100f04d7ec881b8b4f3bbde8d606d427
3
+ size 34553495200
Qwen1.5-32B-Chat-fp16.gguf/Qwen1.5-32B-Chat-fp16_part_a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20a620bd1732a6f3d44885745866d45c8860c1189c9201143ed9a5a7e11c85fc
3
+ size 32516325185
Qwen1.5-32B-Chat-fp16.gguf/Qwen1.5-32B-Chat-fp16_part_b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ffd8eea60d163c9cb3bdeb6d5efae743b0b1f7cd0a4ec9acadbff0a90e31e8
3
+ size 32516325183
Qwen1.5-32B-Chat-fp16.gguf/combine.sh ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ #!/bin/bash
2
+ cat Qwen1.5-32B-Chat-fp16_part_* > "Qwen1.5-32B-Chat-fp16.gguf"
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: tongyi-qianwen
4
+ license_link: >-
5
+ https://huggingface.co/Qwen/Qwen1.5-32B-Chat/blob/main/LICENSE
6
+ language:
7
+ - en
8
+ pipeline_tag: text-generation
9
+ tags:
10
+ - chat
11
+ quantized_by: bartowski
12
+ ---
13
+
14
+ ## Llamacpp Quantizations of Qwen1.5-32B-Chat
15
+
16
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2589">b2589</a> for quantization.
17
+
18
+ Original model: https://huggingface.co/Qwen/Qwen1.5-32B-Chat
19
+
20
+ Download a file (not the whole branch) from below:
21
+
22
+ | Filename | Quant type | File Size | Description |
23
+ | -------- | ---------- | --------- | ----------- |
24
+ | [Qwen1.5-32B-Chat-Q8_0.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q8_0.gguf) | Q8_0 | 34.55GB | Extremely high quality, generally unneeded but max available quant. |
25
+ | [Qwen1.5-32B-Chat-Q6_K.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q6_K.gguf) | Q6_K | 26.67GB | Very high quality, near perfect, *recommended*. |
26
+ | [Qwen1.5-32B-Chat-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q5_K_M.gguf) | Q5_K_M | 23.08GB | High quality, very usable. |
27
+ | [Qwen1.5-32B-Chat-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q5_K_S.gguf) | Q5_K_S | 22.46GB | High quality, very usable. |
28
+ | [Qwen1.5-32B-Chat-Q5_0.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q5_0.gguf) | Q5_0 | 22.46GB | High quality, older format, generally not recommended. |
29
+ | [Qwen1.5-32B-Chat-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q4_K_M.gguf) | Q4_K_M | 19.69GB | Good quality, uses about 4.83 bits per weight. |
30
+ | [Qwen1.5-32B-Chat-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q4_K_S.gguf) | Q4_K_S | 18.64GB | Slightly lower quality with small space savings. |
31
+ | [Qwen1.5-32B-Chat-IQ4_NL.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-IQ4_NL.gguf) | IQ4_NL | 18.68GB | Decent quality, similar to Q4_K_S, new method of quanting, |
32
+ | [Qwen1.5-32B-Chat-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-IQ4_XS.gguf) | IQ4_XS | 17.73GB | Decent quality, new method with similar performance to Q4. |
33
+ | [Qwen1.5-32B-Chat-Q4_0.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q4_0.gguf) | Q4_0 | 18.49GB | Decent quality, older format, generally not recommended. |
34
+ | [Qwen1.5-32B-Chat-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q3_K_L.gguf) | Q3_K_L | 17.11GB | Lower quality but usable, good for low RAM availability. |
35
+ | [Qwen1.5-32B-Chat-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q3_K_M.gguf) | Q3_K_M | 15.81GB | Even lower quality. |
36
+ | [Qwen1.5-32B-Chat-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-IQ3_M.gguf) | IQ3_M | 14.70GB | Medium-low quality, new method with decent performance. |
37
+ | [Qwen1.5-32B-Chat-IQ3_S.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-IQ3_S.gguf) | IQ3_S | 14.32GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
38
+ | [Qwen1.5-32B-Chat-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q3_K_S.gguf) | Q3_K_S | 14.28GB | Low quality, not recommended. |
39
+ | [Qwen1.5-32B-Chat-Q2_K.gguf](https://huggingface.co/bartowski/Qwen1.5-32B-Chat-GGUF/blob/main/Qwen1.5-32B-Chat-Q2_K.gguf) | Q2_K | 12.22GB | Extremely low quality, *not* recommended. |
40
+
41
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski