Hugging Face's logo

mradermacher
/
Brunhilde-13b-v3-GGUF

Transformers
GGUF
English
Mixture of Experts
Merge
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b7a3058
·
verified ·
1 Parent(s): 7448484

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -36,7 +36,7 @@ more details, including on how to concatenate multi-part files.
36
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q3_K_L.gguf) | Q3_K_L | 7.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.IQ4_XS.gguf) | IQ4_XS | 7.3 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q4_0.gguf) | Q4_0 | 7.7 | fast, low quality |
39
- | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.IQ4_NL.gguf) | IQ4_NL | 7.7 | slightly worse than Q4_K_S |
40
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q4_K_S.gguf) | Q4_K_S | 7.7 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q4_K_M.gguf) | Q4_K_M | 8.2 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q5_K_S.gguf) | Q5_K_S | 9.3 | |
@@ -44,7 +44,6 @@ more details, including on how to concatenate multi-part files.
44
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q6_K.gguf) | Q6_K | 11.0 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q8_0.gguf) | Q8_0 | 14.1 | fast, best quality |
46
 
47
-
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
50
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q3_K_L.gguf) | Q3_K_L | 7.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.IQ4_XS.gguf) | IQ4_XS | 7.3 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q4_0.gguf) | Q4_0 | 7.7 | fast, low quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.IQ4_NL.gguf) | IQ4_NL | 7.7 | prefer IQ4_XS |
40
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q4_K_S.gguf) | Q4_K_S | 7.7 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q4_K_M.gguf) | Q4_K_M | 8.2 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q5_K_S.gguf) | Q5_K_S | 9.3 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q6_K.gguf) | Q6_K | 11.0 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Brunhilde-13b-v3-GGUF/resolve/main/Brunhilde-13b-v3.Q8_0.gguf) | Q8_0 | 14.1 | fast, best quality |
46
 
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
49