Hugging Face's logo

mradermacher
/
Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF

Transformers
GGUF
English
Merge
programming
code generation
code
coding
coder
chat
brainstorm
qwen
qwen3
qwencoder
brainstorm20x
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
4f00163
·
verified ·
1 Parent(s): 66d3dba

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md CHANGED
@@ -1,3 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +34,67 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx
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
+ - merge
12
+ - programming
13
+ - code generation
14
+ - code
15
+ - coding
16
+ - coder
17
+ - chat
18
+ - code
19
+ - chat
20
+ - brainstorm
21
+ - qwen
22
+ - qwen3
23
+ - qwencoder
24
+ - brainstorm20x
25
+ ---
26
+ ## About
27
+
28
  <!-- ### quantize_version: 2 -->
29
  <!-- ### output_tensor_quantised: 1 -->
30
  <!-- ### convert_type: hf -->
 
34
  <!-- ### quants_skip: -->
35
  <!-- ### skip_mmproj: -->
36
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx
37
+
38
+ <!-- provided-files -->
39
+
40
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF).***
41
+
42
+ static quants are available at https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-GGUF
43
+ ## Usage
44
+
45
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
46
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
47
+ more details, including on how to concatenate multi-part files.
48
+
49
+ ## Provided Quants
50
+
51
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
52
+
53
+ | Link | Type | Size/GB | Notes |
54
+ |:-----|:-----|--------:|:------|
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
56
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate |
57
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ1_M.gguf) | i1-IQ1_M | 1.7 | mostly desperate |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.9 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.0 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ2_S.gguf) | i1-IQ2_S | 2.1 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ2_M.gguf) | i1-IQ2_M | 2.3 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.3 | very low quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q2_K.gguf) | i1-Q2_K | 2.5 | IQ3_XXS probably better |
64
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.5 | lower quality |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.7 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.8 | IQ3_XS probably better |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ3_S.gguf) | i1-IQ3_S | 2.8 | beats Q3_K* |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ3_M.gguf) | i1-IQ3_M | 2.9 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.1 | IQ3_S probably better |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.4 | IQ3_M probably better |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.4 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q4_0.gguf) | i1-Q4_0 | 3.6 | fast, low quality |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-IQ4_NL.gguf) | i1-IQ4_NL | 3.6 | prefer IQ4_XS |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.6 | optimal size/speed/quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q4_K_M.gguf) | i1-Q4_K_M | 3.7 | fast, recommended |
76
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q4_1.gguf) | i1-Q4_1 | 3.9 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.2 | |
78
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.3 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx-i1-GGUF/resolve/main/Qwen3-Instruct-F16-6B-Brainstorm20x-128k-ctx.i1-Q6_K.gguf) | i1-Q6_K | 5.0 | practically like static Q6_K |
80
+
81
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
82
+ types (lower is better):
83
+
84
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
85
+
86
+ And here are Artefact2's thoughts on the matter:
87
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
88
+
89
+ ## FAQ / Model Request
90
+
91
+ See https://huggingface.co/mradermacher/model_requests for some answers to
92
+ questions you might have and/or if you want some other model quantized.
93
+
94
+ ## Thanks
95
+
96
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
97
+ me use its servers and providing upgrades to my workstation to enable
98
+ 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.
99
+
100
+ <!-- end -->