mradermacher commited on
Commit
83bf446
·
verified ·
1 Parent(s): 1e99833

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md CHANGED
@@ -1,3 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +46,67 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ mradermacher:
8
+ readme_rev: 1
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - programming
12
+ - code generation
13
+ - code
14
+ - coding
15
+ - coder
16
+ - chat
17
+ - code
18
+ - chat
19
+ - brainstorm
20
+ - qwen
21
+ - qwen3
22
+ - qwencoder
23
+ - brainstorm 20x
24
+ - creative
25
+ - all uses cases
26
+ - Jan-V1
27
+ - Deep Space Nine
28
+ - DS9
29
+ - horror
30
+ - science fiction
31
+ - fantasy
32
+ - Star Trek
33
+ - finetune
34
+ - thinking
35
+ - reasoning
36
+ - unsloth
37
+ ---
38
+ ## About
39
+
40
  <!-- ### quantize_version: 2 -->
41
  <!-- ### output_tensor_quantised: 1 -->
42
  <!-- ### convert_type: hf -->
 
46
  <!-- ### quants_skip: -->
47
  <!-- ### skip_mmproj: -->
48
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B
49
+
50
+ <!-- provided-files -->
51
+
52
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF).***
53
+
54
+ static quants are available at https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-GGUF
55
+ ## Usage
56
+
57
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
58
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
59
+ more details, including on how to concatenate multi-part files.
60
+
61
+ ## Provided Quants
62
+
63
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
64
+
65
+ | Link | Type | Size/GB | Notes |
66
+ |:-----|:-----|--------:|:------|
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.2 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.3 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.4 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.4 | very low quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q2_K.gguf) | i1-Q2_K | 2.6 | IQ3_XXS probably better |
76
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality |
77
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.9 | |
78
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* |
80
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.1 | |
81
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.3 | IQ3_S probably better |
82
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.5 | IQ3_M probably better |
83
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.6 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q4_0.gguf) | i1-Q4_0 | 3.8 | fast, low quality |
85
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 3.8 | prefer IQ4_XS |
86
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.8 | optimal size/speed/quality |
87
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.0 | fast, recommended |
88
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q4_1.gguf) | i1-Q4_1 | 4.1 | |
89
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.5 | |
90
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.6 | |
91
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B-i1-GGUF/resolve/main/Qwen3-ST-Deep-Space-Nine-v3-256k-ctx-6B.i1-Q6_K.gguf) | i1-Q6_K | 5.3 | practically like static Q6_K |
92
+
93
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
94
+ types (lower is better):
95
+
96
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
97
+
98
+ And here are Artefact2's thoughts on the matter:
99
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
100
+
101
+ ## FAQ / Model Request
102
+
103
+ See https://huggingface.co/mradermacher/model_requests for some answers to
104
+ questions you might have and/or if you want some other model quantized.
105
+
106
+ ## Thanks
107
+
108
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
109
+ me use its servers and providing upgrades to my workstation to enable
110
+ 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.
111
+
112
+ <!-- end -->