Hugging Face's logo

mradermacher
/
Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF

Transformers
GGUF
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
Qwen3-30B-A3B-Thinking-2507
Qwen3-30B-A3B
mixture of experts
128 experts
10 active experts
256k context
qwen3
finetune
brainstorm 40x
brainstorm
thinking
reasoning
qwen3_moe
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
a6bc5a3
·
verified ·
1 Parent(s): 9f566cd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +107 -0
README.md CHANGED
@@ -1,3 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +55,62 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER
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
+ - moe
33
+ - Qwen3-30B-A3B-Thinking-2507
34
+ - Qwen3-30B-A3B
35
+ - mixture of experts
36
+ - 128 experts
37
+ - 10 active experts
38
+ - 256k context
39
+ - qwen3
40
+ - finetune
41
+ - brainstorm 40x
42
+ - brainstorm
43
+ - thinking
44
+ - reasoning
45
+ - qwen3_moe
46
+ ---
47
+ ## About
48
+
49
  <!-- ### quantize_version: 2 -->
50
  <!-- ### output_tensor_quantised: 1 -->
51
  <!-- ### convert_type: hf -->
 
55
  <!-- ### quants_skip: -->
56
  <!-- ### skip_mmproj: -->
57
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER
58
+
59
+ <!-- provided-files -->
60
+
61
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF).***
62
+
63
+ static quants are available at https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-GGUF
64
+ ## Usage
65
+
66
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
67
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
68
+ more details, including on how to concatenate multi-part files.
69
+
70
+ ## Provided Quants
71
+
72
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
73
+
74
+ | Link | Type | Size/GB | Notes |
75
+ |:-----|:-----|--------:|:------|
76
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.imatrix.gguf) | imatrix | 0.3 | imatrix file (for creating your own qwuants) |
77
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ1_S.gguf) | i1-IQ1_S | 11.1 | for the desperate |
78
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ1_M.gguf) | i1-IQ1_M | 12.2 | mostly desperate |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 14.2 | |
80
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ2_XS.gguf) | i1-IQ2_XS | 15.7 | |
81
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ2_S.gguf) | i1-IQ2_S | 16.1 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ2_M.gguf) | i1-IQ2_M | 17.6 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q2_K_S.gguf) | i1-Q2_K_S | 18.2 | very low quality |
84
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q2_K.gguf) | i1-Q2_K | 19.5 | IQ3_XXS probably better |
85
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 20.6 | lower quality |
86
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q3_K_S.gguf) | i1-Q3_K_S | 23.1 | IQ3_XS probably better |
87
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ3_M.gguf) | i1-IQ3_M | 23.4 | |
88
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q3_K_M.gguf) | i1-Q3_K_M | 25.5 | IQ3_S probably better |
89
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q3_K_L.gguf) | i1-Q3_K_L | 27.6 | IQ3_M probably better |
90
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-IQ4_XS.gguf) | i1-IQ4_XS | 28.4 | |
91
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q4_K_S.gguf) | i1-Q4_K_S | 30.3 | optimal size/speed/quality |
92
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q4_K_M.gguf) | i1-Q4_K_M | 32.2 | fast, recommended |
93
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q5_K_S.gguf) | i1-Q5_K_S | 36.6 | |
94
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q5_K_M.gguf) | i1-Q5_K_M | 37.8 | |
95
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUF/resolve/main/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER.i1-Q6_K.gguf) | i1-Q6_K | 43.6 | practically like static Q6_K |
96
+
97
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
98
+ types (lower is better):
99
+
100
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
101
+
102
+ And here are Artefact2's thoughts on the matter:
103
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
104
+
105
+ ## FAQ / Model Request
106
+
107
+ See https://huggingface.co/mradermacher/model_requests for some answers to
108
+ questions you might have and/or if you want some other model quantized.
109
+
110
+ ## Thanks
111
+
112
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
113
+ me use its servers and providing upgrades to my workstation to enable
114
+ 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.
115
+
116
+ <!-- end -->