Hugging Face's logo

mradermacher
/
loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF

Text Generation
Transformers
GGUF
English
qwen3
qwen3moe
mixture-of-experts
llm
instruction-following
agentic-ai
tool-use
low-resource
edge-ai
from-scratch
causal-lm
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
b4327eb
·
verified ·
1 Parent(s): a1c2d82

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/kshitijthakkar/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: kshitijthakkar/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned
3
+ datasets:
4
+ - kshitijthakkar/loggenix-mc-oraca-agentinstruct-1m-v1
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
+ - qwen3
14
+ - qwen3moe
15
+ - mixture-of-experts
16
+ - llm
17
+ - text-generation
18
+ - instruction-following
19
+ - agentic-ai
20
+ - tool-use
21
+ - low-resource
22
+ - edge-ai
23
+ - from-scratch
24
+ - causal-lm
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/kshitijthakkar/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned
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#loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF).***
41
+
42
+ static quants are available at https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-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/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
56
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ1_S.gguf) | i1-IQ1_S | 0.2 | for the desperate |
57
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ1_M.gguf) | i1-IQ1_M | 0.2 | mostly desperate |
58
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.2 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.2 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ2_S.gguf) | i1-IQ2_S | 0.2 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ2_M.gguf) | i1-IQ2_M | 0.2 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.2 | lower quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.2 | very low quality |
64
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q2_K.gguf) | i1-Q2_K | 0.2 | IQ3_XXS probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.2 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ3_S.gguf) | i1-IQ3_S | 0.2 | beats Q3_K* |
67
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.2 | IQ3_XS probably better |
68
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ3_M.gguf) | i1-IQ3_M | 0.2 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.2 | IQ3_S probably better |
70
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.2 | IQ3_M probably better |
71
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.2 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q4_0.gguf) | i1-Q4_0 | 0.2 | fast, low quality |
73
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.2 | prefer IQ4_XS |
74
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.2 | optimal size/speed/quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.2 | fast, recommended |
76
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q4_1.gguf) | i1-Q4_1 | 0.2 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.2 | |
78
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.2 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned-i1-GGUF/resolve/main/loggenix-moe-0.12B-A0.08B-e5-lr5e4-b16-3060-v2-finetuned.i1-Q6_K.gguf) | i1-Q6_K | 0.2 | 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 -->