Hugging Face's logo

mradermacher
/
Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF

Transformers
GGUF
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
qwen3
finetune
brainstorm 20x
brainstorm
optional thinking
creative
all use cases
QiMing
QiMing-holos
bagua
decision-making
strategic-analysis
cognitive-architecture
philosophy-driven-ai
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
45144b7
·
verified ·
1 Parent(s): 9618fc4

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +113 -0
README.md CHANGED
@@ -1,3 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +56,67 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-16B-QiMing-V1.0-Total-Recall-Light
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen3-16B-QiMing-V1.0-Total-Recall-Light
3
+ language:
4
+ - en
5
+ - fr
6
+ - zh
7
+ - de
8
+ library_name: transformers
9
+ license: apache-2.0
10
+ mradermacher:
11
+ readme_rev: 1
12
+ quantized_by: mradermacher
13
+ tags:
14
+ - programming
15
+ - code generation
16
+ - code
17
+ - codeqwen
18
+ - programming
19
+ - code generation
20
+ - code
21
+ - codeqwen
22
+ - moe
23
+ - coding
24
+ - coder
25
+ - qwen2
26
+ - chat
27
+ - qwen
28
+ - qwen-coder
29
+ - chat
30
+ - qwen
31
+ - qwen-coder
32
+ - qwen3
33
+ - finetune
34
+ - brainstorm 20x
35
+ - brainstorm
36
+ - optional thinking
37
+ - creative
38
+ - all use cases
39
+ - QiMing
40
+ - QiMing-holos
41
+ - bagua
42
+ - decision-making
43
+ - strategic-analysis
44
+ - cognitive-architecture
45
+ - chat
46
+ - philosophy-driven-ai
47
+ ---
48
+ ## About
49
+
50
  <!-- ### quantize_version: 2 -->
51
  <!-- ### output_tensor_quantised: 1 -->
52
  <!-- ### convert_type: hf -->
 
56
  <!-- ### quants_skip: -->
57
  <!-- ### skip_mmproj: -->
58
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-16B-QiMing-V1.0-Total-Recall-Light
59
+
60
+ <!-- provided-files -->
61
+
62
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF).***
63
+
64
+ static quants are available at https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-GGUF
65
+ ## Usage
66
+
67
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
68
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
69
+ more details, including on how to concatenate multi-part files.
70
+
71
+ ## Provided Quants
72
+
73
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
74
+
75
+ | Link | Type | Size/GB | Notes |
76
+ |:-----|:-----|--------:|:------|
77
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
78
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ1_S.gguf) | i1-IQ1_S | 4.0 | for the desperate |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ1_M.gguf) | i1-IQ1_M | 4.3 | mostly desperate |
80
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.7 | |
81
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.2 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ2_S.gguf) | i1-IQ2_S | 5.5 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ2_M.gguf) | i1-IQ2_M | 5.9 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.9 | very low quality |
85
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q2_K.gguf) | i1-Q2_K | 6.3 | IQ3_XXS probably better |
86
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.5 | lower quality |
87
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.0 | |
88
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q3_K_S.gguf) | i1-Q3_K_S | 7.3 | IQ3_XS probably better |
89
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ3_S.gguf) | i1-IQ3_S | 7.4 | beats Q3_K* |
90
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ3_M.gguf) | i1-IQ3_M | 7.6 | |
91
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q3_K_M.gguf) | i1-Q3_K_M | 8.1 | IQ3_S probably better |
92
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.7 | IQ3_M probably better |
93
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.9 | |
94
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q4_0.gguf) | i1-Q4_0 | 9.4 | fast, low quality |
95
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-IQ4_NL.gguf) | i1-IQ4_NL | 9.4 | prefer IQ4_XS |
96
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q4_K_S.gguf) | i1-Q4_K_S | 9.4 | optimal size/speed/quality |
97
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.9 | fast, recommended |
98
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q4_1.gguf) | i1-Q4_1 | 10.3 | |
99
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q5_K_S.gguf) | i1-Q5_K_S | 11.3 | |
100
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q5_K_M.gguf) | i1-Q5_K_M | 11.5 | |
101
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-16B-QiMing-V1.0-Total-Recall-Light-i1-GGUF/resolve/main/Qwen3-16B-QiMing-V1.0-Total-Recall-Light.i1-Q6_K.gguf) | i1-Q6_K | 13.3 | practically like static Q6_K |
102
+
103
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
104
+ types (lower is better):
105
+
106
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
107
+
108
+ And here are Artefact2's thoughts on the matter:
109
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
110
+
111
+ ## FAQ / Model Request
112
+
113
+ See https://huggingface.co/mradermacher/model_requests for some answers to
114
+ questions you might have and/or if you want some other model quantized.
115
+
116
+ ## Thanks
117
+
118
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
119
+ me use its servers and providing upgrades to my workstation to enable
120
+ 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.
121
+
122
+ <!-- end -->