Hugging Face's logo

mradermacher
/
DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF

Transformers
GGUF
reasoning
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
330e5a1
·
verified ·
1 Parent(s): 3423632

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md CHANGED
@@ -1,6 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/lightblue/DeepSeek-R1-Distill-Qwen-14B-Multilingual
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: lightblue/DeepSeek-R1-Distill-Qwen-14B-Multilingual
3
+ datasets:
4
+ - lightblue/reasoning-multilingual-R1-Llama-70B-train
5
+ language:
6
+ - am
7
+ - ar
8
+ - bn
9
+ - zh
10
+ - cs
11
+ - nl
12
+ - en
13
+ - fr
14
+ - de
15
+ - el
16
+ - ha
17
+ - he
18
+ - hi
19
+ - id
20
+ - it
21
+ - ja
22
+ - jv
23
+ - km
24
+ - ko
25
+ - lo
26
+ - ms
27
+ - mr
28
+ - fa
29
+ - pl
30
+ - pt
31
+ - ro
32
+ - ru
33
+ - es
34
+ - sw
35
+ - sv
36
+ - tl
37
+ - ta
38
+ - te
39
+ - th
40
+ - tr
41
+ - uk
42
+ - ur
43
+ - vi
44
+ library_name: transformers
45
+ license: apache-2.0
46
+ quantized_by: mradermacher
47
+ tags:
48
+ - reasoning
49
+ ---
50
+ ## About
51
+
52
  <!-- ### quantize_version: 2 -->
53
  <!-- ### output_tensor_quantised: 1 -->
54
  <!-- ### convert_type: hf -->
55
  <!-- ### vocab_type: -->
56
  <!-- ### tags: -->
57
  static quants of https://huggingface.co/lightblue/DeepSeek-R1-Distill-Qwen-14B-Multilingual
58
+
59
+ <!-- provided-files -->
60
+ weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
61
+ ## Usage
62
+
63
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
64
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
65
+ more details, including on how to concatenate multi-part files.
66
+
67
+ ## Provided Quants
68
+
69
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
70
+
71
+ | Link | Type | Size/GB | Notes |
72
+ |:-----|:-----|--------:|:------|
73
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q2_K.gguf) | Q2_K | 5.9 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
75
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
76
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
78
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
79
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
80
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
81
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
83
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-Multilingual-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Multilingual.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
84
+
85
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
86
+ types (lower is better):
87
+
88
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
89
+
90
+ And here are Artefact2's thoughts on the matter:
91
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
92
+
93
+ ## FAQ / Model Request
94
+
95
+ See https://huggingface.co/mradermacher/model_requests for some answers to
96
+ questions you might have and/or if you want some other model quantized.
97
+
98
+ ## Thanks
99
+
100
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
101
+ me use its servers and providing upgrades to my workstation to enable
102
+ this work in my free time.
103
+
104
+ <!-- end -->