Hugging Face's logo

mradermacher
/
NeuralSpanish-7b-v1-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
ecastera/eva-mistral-dolphin-7b-spanish
ecastera/ecastera-eva-westlake-7b-spanish
ecastera/eva-mistral-catmacaroni-7b-spanish
Kukedlc/NeuralSirKrishna-Spanish-FT
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
644b7dd
•
1 Parent(s): 5f41034

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -41,14 +41,13 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
42
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
44
- | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
47
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
48
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
50
 
51
-
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):
54
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
42
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
47
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
48
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/NeuralSpanish-7b-v1-GGUF/resolve/main/NeuralSpanish-7b-v1.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
50
 
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
53