Hugging Face's logo

mradermacher
/
Lowke-2x7B-v1-GGUF

Transformers
GGUF
English
Mixture of Experts
frankenmoe
Merge
mergekit
lazymergekit
mlabonne/AlphaMonarch-7B
ozayezerceli/Threnystril-v2.0-7B-slerp
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
4aed6db
•
1 Parent(s): 546feee

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -42,14 +42,13 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.IQ4_XS.gguf) | IQ4_XS | 7.2 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q4_0.gguf) | Q4_0 | 7.5 | fast, low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q4_K_S.gguf) | Q4_K_S | 7.6 | fast, recommended |
45
- | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.IQ4_NL.gguf) | IQ4_NL | 7.6 | slightly worse than Q4_K_S |
46
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q5_K_M.gguf) | Q5_K_M | 9.4 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
51
 
52
-
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.IQ4_XS.gguf) | IQ4_XS | 7.2 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q4_0.gguf) | Q4_0 | 7.5 | fast, low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q4_K_S.gguf) | Q4_K_S | 7.6 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.IQ4_NL.gguf) | IQ4_NL | 7.6 | prefer IQ4_XS |
46
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q5_K_M.gguf) | Q5_K_M | 9.4 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Lowke-2x7B-v1-GGUF/resolve/main/Lowke-2x7B-v1.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
51
 
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):
54