Hugging Face's logo

mradermacher
/
Abomination-merge-attempt-12B-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
Trappu/Magnum-Picaro-0.7-v2-12b
DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
2fa06ce
·
verified ·
1 Parent(s): c7b062f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -35,8 +35,15 @@ more details, including on how to concatenate multi-part files.
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
  | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q2_K.gguf) | Q2_K | 4.9 | |
 
38
  | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
 
 
 
 
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
42
  types (lower is better):
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
  | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q2_K.gguf) | Q2_K | 4.9 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q3_K_S.gguf) | Q3_K_S | 5.6 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q3_K_L.gguf) | Q3_K_L | 6.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q5_K_S.gguf) | Q5_K_S | 8.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q5_K_M.gguf) | Q5_K_M | 8.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q6_K.gguf) | Q6_K | 10.2 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Abomination-merge-attempt-12B-GGUF/resolve/main/Abomination-merge-attempt-12B.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):