Hugging Face's logo

mradermacher
/
Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF

Transformers
GGUF
English
Merge
programming
code generation
code
codeqwen
coding
coder
qwen3
chat
qwen
qwen-coder
reasoning
thinking
r1
cot
deepseek
40k context
general usage
problem solving
brainstorming
solve riddles
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
73999f0
·
verified ·
1 Parent(s): 6ea2590

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +100 -0
README.md CHANGED
@@ -1,6 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-Zero-Coder-Reasoning-0.8B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen3-Zero-Coder-Reasoning-0.8B
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
+ - codeqwen
16
+ - coding
17
+ - coder
18
+ - qwen3
19
+ - chat
20
+ - qwen
21
+ - qwen-coder
22
+ - code
23
+ - chat
24
+ - reasoning
25
+ - thinking
26
+ - r1
27
+ - cot
28
+ - deepseek
29
+ - 40k context
30
+ - general usage
31
+ - problem solving
32
+ - brainstorming
33
+ - solve riddles
34
+ - general usage
35
+ ---
36
+ ## About
37
+
38
  <!-- ### quantize_version: 2 -->
39
  <!-- ### output_tensor_quantised: 1 -->
40
  <!-- ### convert_type: hf -->
41
  <!-- ### vocab_type: -->
42
  <!-- ### tags: nicoboss -->
43
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-Zero-Coder-Reasoning-0.8B
44
+
45
+ <!-- provided-files -->
46
+
47
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF).***
48
+
49
+ static quants are available at https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-GGUF
50
+ ## Usage
51
+
52
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
53
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
54
+ more details, including on how to concatenate multi-part files.
55
+
56
+ ## Provided Quants
57
+
58
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
59
+
60
+ | Link | Type | Size/GB | Notes |
61
+ |:-----|:-----|--------:|:------|
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate |
64
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.5 | very low quality |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.5 | lower quality |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q2_K.gguf) | i1-Q2_K | 0.5 | IQ3_XXS probably better |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.5 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.5 | beats Q3_K* |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.5 | IQ3_XS probably better |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.5 | |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.6 | IQ3_S probably better |
76
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.6 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.6 | IQ3_M probably better |
78
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.6 | prefer IQ4_XS |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q4_0.gguf) | i1-Q4_0 | 0.6 | fast, low quality |
80
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.6 | optimal size/speed/quality |
81
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.6 | fast, recommended |
82
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q4_1.gguf) | i1-Q4_1 | 0.6 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.7 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.7 | |
85
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Zero-Coder-Reasoning-0.8B-i1-GGUF/resolve/main/Qwen3-Zero-Coder-Reasoning-0.8B.i1-Q6_K.gguf) | i1-Q6_K | 0.8 | practically like static Q6_K |
86
+
87
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
88
+ types (lower is better):
89
+
90
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
91
+
92
+ And here are Artefact2's thoughts on the matter:
93
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
94
+
95
+ ## FAQ / Model Request
96
+
97
+ See https://huggingface.co/mradermacher/model_requests for some answers to
98
+ questions you might have and/or if you want some other model quantized.
99
+
100
+ ## Thanks
101
+
102
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
103
+ me use its servers and providing upgrades to my workstation to enable
104
+ 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.
105
+
106
+ <!-- end -->