Hugging Face's logo

mradermacher
/
Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF

Transformers
GGUF
English
Uncensored
Abliterated
Cubed Reasoning
QwQ-32B
reasoning
thinking
r1
cot
deepseek
Qwen2.5
Hermes
DeepHermes
DeepSeek
DeepSeek-R1-Distill
128k context
Merge
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
d1a9cd1
·
verified ·
1 Parent(s): dabeec8

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md CHANGED
@@ -1,6 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ tags:
8
+ - Uncensored
9
+ - Abliterated
10
+ - Cubed Reasoning
11
+ - QwQ-32B
12
+ - reasoning
13
+ - thinking
14
+ - r1
15
+ - cot
16
+ - deepseek
17
+ - Qwen2.5
18
+ - Hermes
19
+ - DeepHermes
20
+ - DeepSeek
21
+ - DeepSeek-R1-Distill
22
+ - 128k context
23
+ - merge
24
+ ---
25
+ ## About
26
+
27
  <!-- ### quantize_version: 2 -->
28
  <!-- ### output_tensor_quantised: 1 -->
29
  <!-- ### convert_type: hf -->
30
  <!-- ### vocab_type: -->
31
  <!-- ### tags: nicoboss -->
32
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored
33
+
34
+ <!-- provided-files -->
35
+ static quants are available at https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-GGUF
36
+ ## Usage
37
+
38
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
39
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
40
+ more details, including on how to concatenate multi-part files.
41
+
42
+ ## Provided Quants
43
+
44
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
45
+
46
+ | Link | Type | Size/GB | Notes |
47
+ |:-----|:-----|--------:|:------|
48
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ1_S.gguf) | i1-IQ1_S | 7.8 | for the desperate |
49
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ1_M.gguf) | i1-IQ1_M | 8.5 | mostly desperate |
50
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.6 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.6 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ2_S.gguf) | i1-IQ2_S | 11.1 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 12.0 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q2_K.gguf) | i1-Q2_K | 13.1 | IQ3_XXS probably better |
56
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.7 | lower quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.6 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.3 | IQ3_XS probably better |
59
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ3_S.gguf) | i1-IQ3_S | 15.4 | beats Q3_K* |
60
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ3_M.gguf) | i1-IQ3_M | 15.8 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.0 | IQ3_S probably better |
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.4 | IQ3_M probably better |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.8 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q4_0.gguf) | i1-Q4_0 | 19.9 | fast, low quality |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.0 | optimal size/speed/quality |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.1 | fast, recommended |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q4_1.gguf) | i1-Q4_1 | 22.0 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.1 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.7 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-i1-GGUF/resolve/main/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored.i1-Q6_K.gguf) | i1-Q6_K | 28.6 | practically like static Q6_K |
71
+
72
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
73
+ types (lower is better):
74
+
75
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
76
+
77
+ And here are Artefact2's thoughts on the matter:
78
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
79
+
80
+ ## FAQ / Model Request
81
+
82
+ See https://huggingface.co/mradermacher/model_requests for some answers to
83
+ questions you might have and/or if you want some other model quantized.
84
+
85
+ ## Thanks
86
+
87
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
88
+ me use its servers and providing upgrades to my workstation to enable
89
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
90
+
91
+ <!-- end -->