Hugging Face's logo

mradermacher
/
Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF

Transformers
GGUF
English
Merge
programming
code generation
code
coding
coder
chat
brainstorm
qwen
qwen3
qwencoder
brainstorm20x
esper
esper-3
valiant
valiant-labs
qwen-3
qwen-3-14b
14b
reasoning
code-instruct
python
javascript
dev-ops
jenkins
terraform
scripting
powershell
azure
aws
gcp
cloud
problem-solving
architect
engineer
developer
creative
analytical
expert
rationality
conversational
instruct
float32
imatrix
Model card Files
xet
Community
mradermacher commited on
Commit
55c3b89
·
verified ·
1 Parent(s): d1e1505

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +128 -0
README.md CHANGED
@@ -1,3 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +72,66 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x
3
+ datasets:
4
+ - sequelbox/Titanium2.1-DeepSeek-R1
5
+ - sequelbox/Tachibana2-DeepSeek-R1
6
+ - sequelbox/Raiden-DeepSeek-R1
7
+ language:
8
+ - en
9
+ library_name: transformers
10
+ license: apache-2.0
11
+ mradermacher:
12
+ readme_rev: 1
13
+ quantized_by: mradermacher
14
+ tags:
15
+ - merge
16
+ - programming
17
+ - code generation
18
+ - code
19
+ - coding
20
+ - coder
21
+ - chat
22
+ - code
23
+ - chat
24
+ - brainstorm
25
+ - qwen
26
+ - qwen3
27
+ - qwencoder
28
+ - brainstorm20x
29
+ - esper
30
+ - esper-3
31
+ - valiant
32
+ - valiant-labs
33
+ - qwen
34
+ - qwen-3
35
+ - qwen-3-14b
36
+ - 14b
37
+ - reasoning
38
+ - code
39
+ - code-instruct
40
+ - python
41
+ - javascript
42
+ - dev-ops
43
+ - jenkins
44
+ - terraform
45
+ - scripting
46
+ - powershell
47
+ - azure
48
+ - aws
49
+ - gcp
50
+ - cloud
51
+ - problem-solving
52
+ - architect
53
+ - engineer
54
+ - developer
55
+ - creative
56
+ - analytical
57
+ - expert
58
+ - rationality
59
+ - conversational
60
+ - chat
61
+ - instruct
62
+ - float32
63
+ ---
64
+ ## About
65
+
66
  <!-- ### quantize_version: 2 -->
67
  <!-- ### output_tensor_quantised: 1 -->
68
  <!-- ### convert_type: hf -->
 
72
  <!-- ### quants_skip: -->
73
  <!-- ### skip_mmproj: -->
74
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x
75
+
76
+ <!-- provided-files -->
77
+
78
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF).***
79
+
80
+ static quants are available at https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-GGUF
81
+ ## Usage
82
+
83
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
84
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
85
+ more details, including on how to concatenate multi-part files.
86
+
87
+ ## Provided Quants
88
+
89
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
90
+
91
+ | Link | Type | Size/GB | Notes |
92
+ |:-----|:-----|--------:|:------|
93
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
94
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ1_S.gguf) | i1-IQ1_S | 5.0 | for the desperate |
95
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ1_M.gguf) | i1-IQ1_M | 5.4 | mostly desperate |
96
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.1 | |
97
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.6 | |
98
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ2_S.gguf) | i1-IQ2_S | 7.0 | |
99
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ2_M.gguf) | i1-IQ2_M | 7.5 | |
100
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q2_K_S.gguf) | i1-Q2_K_S | 7.6 | very low quality |
101
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q2_K.gguf) | i1-Q2_K | 8.2 | IQ3_XXS probably better |
102
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.4 | lower quality |
103
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ3_XS.gguf) | i1-IQ3_XS | 9.0 | |
104
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.5 | IQ3_XS probably better |
105
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ3_S.gguf) | i1-IQ3_S | 9.5 | beats Q3_K* |
106
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ3_M.gguf) | i1-IQ3_M | 9.8 | |
107
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.4 | IQ3_S probably better |
108
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.3 | IQ3_M probably better |
109
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.6 | |
110
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality |
111
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.2 | optimal size/speed/quality |
112
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.9 | fast, recommended |
113
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q4_1.gguf) | i1-Q4_1 | 13.4 | |
114
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.7 | |
115
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q5_K_M.gguf) | i1-Q5_K_M | 15.0 | |
116
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-i1-GGUF/resolve/main/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x.i1-Q6_K.gguf) | i1-Q6_K | 17.4 | practically like static Q6_K |
117
+
118
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
119
+ types (lower is better):
120
+
121
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
122
+
123
+ And here are Artefact2's thoughts on the matter:
124
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
125
+
126
+ ## FAQ / Model Request
127
+
128
+ See https://huggingface.co/mradermacher/model_requests for some answers to
129
+ questions you might have and/or if you want some other model quantized.
130
+
131
+ ## Thanks
132
+
133
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
134
+ me use its servers and providing upgrades to my workstation to enable
135
+ 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.
136
+
137
+ <!-- end -->