mradermacher commited on
Commit
f65b375
·
verified ·
1 Parent(s): da9ab2d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +114 -0
README.md CHANGED
@@ -1,3 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +70,54 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  static quants of https://huggingface.co/sequelbox/Qwen3-4B-Thinking-2507-DES-Reasoning
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sequelbox/Qwen3-4B-Thinking-2507-DES-Reasoning
3
+ datasets:
4
+ - sequelbox/DES-Reasoning-DeepSeek-V3.1
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ license: apache-2.0
9
+ mradermacher:
10
+ readme_rev: 1
11
+ quantized_by: mradermacher
12
+ tags:
13
+ - des-reasoning
14
+ - qwen
15
+ - qwen-3
16
+ - qwen-3-4b
17
+ - qwen3-4b-thinking-2507
18
+ - 4b
19
+ - reasoning
20
+ - discrete-event-simulation
21
+ - simulation
22
+ - SimPy
23
+ - Python
24
+ - scripting
25
+ - logic
26
+ - analysis
27
+ - programming
28
+ - knowledge
29
+ - root-cause-analysis
30
+ - economics
31
+ - strategy
32
+ - business
33
+ - business-management
34
+ - finance
35
+ - law
36
+ - supply-chain
37
+ - manufacturing
38
+ - telecommunications
39
+ - transportation
40
+ - healthcare
41
+ - logistics
42
+ - energy
43
+ - retail
44
+ - construction
45
+ - agriculture
46
+ - information-technology
47
+ - environment
48
+ - software-engineering
49
+ - cybersecurity
50
+ - architecture
51
+ - energy
52
+ - politics
53
+ - problem-solving
54
+ - creative
55
+ - analytical
56
+ - expert
57
+ - rationality
58
+ - conversational
59
+ - chat
60
+ - instruct
61
+ ---
62
+ ## About
63
+
64
  <!-- ### quantize_version: 2 -->
65
  <!-- ### output_tensor_quantised: 1 -->
66
  <!-- ### convert_type: hf -->
 
70
  <!-- ### quants_skip: -->
71
  <!-- ### skip_mmproj: -->
72
  static quants of https://huggingface.co/sequelbox/Qwen3-4B-Thinking-2507-DES-Reasoning
73
+
74
+ <!-- provided-files -->
75
+
76
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF).***
77
+
78
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-i1-GGUF
79
+ ## Usage
80
+
81
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
82
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
83
+ more details, including on how to concatenate multi-part files.
84
+
85
+ ## Provided Quants
86
+
87
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
88
+
89
+ | Link | Type | Size/GB | Notes |
90
+ |:-----|:-----|--------:|:------|
91
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q2_K.gguf) | Q2_K | 1.8 | |
92
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q3_K_S.gguf) | Q3_K_S | 2.0 | |
93
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality |
94
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q3_K_L.gguf) | Q3_K_L | 2.3 | |
95
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.IQ4_XS.gguf) | IQ4_XS | 2.4 | |
96
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended |
97
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended |
98
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q5_K_S.gguf) | Q5_K_S | 2.9 | |
99
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q5_K_M.gguf) | Q5_K_M | 3.0 | |
100
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q6_K.gguf) | Q6_K | 3.4 | very good quality |
101
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality |
102
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-DES-Reasoning-GGUF/resolve/main/Qwen3-4B-Thinking-2507-DES-Reasoning.f16.gguf) | f16 | 8.2 | 16 bpw, overkill |
103
+
104
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
105
+ types (lower is better):
106
+
107
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
108
+
109
+ And here are Artefact2's thoughts on the matter:
110
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
111
+
112
+ ## FAQ / Model Request
113
+
114
+ See https://huggingface.co/mradermacher/model_requests for some answers to
115
+ questions you might have and/or if you want some other model quantized.
116
+
117
+ ## Thanks
118
+
119
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
120
+ me use its servers and providing upgrades to my workstation to enable
121
+ this work in my free time.
122
+
123
+ <!-- end -->