Hugging Face's logo

mradermacher
/
NexoNimbus-7B-GGUF

Transformers
GGUF
English
Merge
abideen/DareVox-7B
udkai/Garrulus
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
fbb832f
•
1 Parent(s): 83f671c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -38,14 +38,13 @@ more details, including on how to concatenate multi-part files.
38
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
39
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
41
- | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
42
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
43
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
45
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
47
 
48
-
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
51
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
39
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
42
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
43
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
45
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/NexoNimbus-7B-GGUF/resolve/main/NexoNimbus-7B.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
47
 
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
50