Hugging Face's logo

mradermacher
/
MythoMax-L2-13b-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
73d51ad
•
1 Parent(s): 9c867ee

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -0
README.md CHANGED
@@ -1 +1,56 @@
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/Gryphe/MythoMax-L2-13b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: transformers
5
+ license: other
6
+ quantized_by: mradermacher
7
+ ---
8
+ ## About
9
+
10
  static quants of https://huggingface.co/Gryphe/MythoMax-L2-13b
11
+
12
+
13
+ <!-- provided-files -->
14
+ ## Usage
15
+
16
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
17
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
18
+ more details, including on how to concatenate multi-part files.
19
+
20
+ ## Provided Quants
21
+
22
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
23
+
24
+ | Link | Type | Size/GB | Notes |
25
+ |:-----|:-----|--------:|:------|
26
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q2_K.gguf) | Q2_K | 5.1 | |
27
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.IQ3_XS.gguf) | IQ3_XS | 5.7 | |
28
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.IQ3_S.gguf) | IQ3_S | 6.0 | fast, beats Q3_K* |
29
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q3_K_S.gguf) | Q3_K_S | 6.0 | |
30
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.IQ3_M.gguf) | IQ3_M | 6.3 | |
31
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q3_K_M.gguf) | Q3_K_M | 6.6 | lower quality |
32
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q3_K_L.gguf) | Q3_K_L | 7.2 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.IQ4_XS.gguf) | IQ4_XS | 7.3 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q4_K_S.gguf) | Q4_K_S | 7.7 | fast, medium quality |
35
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q4_K_M.gguf) | Q4_K_M | 8.2 | fast, medium quality |
36
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q5_K_S.gguf) | Q5_K_S | 9.3 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q5_K_M.gguf) | Q5_K_M | 9.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q6_K.gguf) | Q6_K | 11.0 | very good quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/MythoMax-L2-13b-GGUF/resolve/main/MythoMax-L2-13b.Q8_0.gguf) | Q8_0 | 14.1 | fast, best quality |
40
+
41
+
42
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
43
+ types (lower is better):
44
+
45
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
46
+
47
+ And here are Artefact2's thoughts on the matter:
48
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
49
+
50
+ ## Thanks
51
+
52
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
53
+ me use its servers and providing upgrades to my workstation to enable
54
+ this work in my free time.
55
+
56
+ <!-- end -->