Hugging Face's logo

mradermacher
/
Norocetacean-20b-10k-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
30463b1
·
verified ·
1 Parent(s): ea73df5

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -39,7 +39,7 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.0 | IQ3_S probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 | |
42
- | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-IQ4_NL.gguf) | i1-IQ4_NL | 11.6 | slightly worse than Q4_K_S |
43
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q4_0.gguf) | i1-Q4_0 | 11.6 | fast, low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.7 | optimal size/speed/quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.3 | fast, recommended |
@@ -47,7 +47,6 @@ more details, including on how to concatenate multi-part files.
47
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.5 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | practically like static Q6_K |
49
 
50
-
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
53
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.0 | IQ3_S probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-IQ4_NL.gguf) | i1-IQ4_NL | 11.6 | prefer IQ4_XS |
43
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q4_0.gguf) | i1-Q4_0 | 11.6 | fast, low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.7 | optimal size/speed/quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.3 | fast, recommended |
 
47
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.5 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Norocetacean-20b-10k-i1-GGUF/resolve/main/Norocetacean-20b-10k.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | practically like static Q6_K |
49
 
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
52