Hugging Face's logo

mradermacher
/
CabraQwen14b-GGUF

Transformers
GGUF
Portuguese
English
text-generation-inference
qwen
brazil
brasil
14b
portuguese
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
d4caa30
•
1 Parent(s): e5fa04c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  base_model: nicolasdec/CabraQwen14b
3
  language:
 
4
  - en
5
  library_name: transformers
6
  license: cc
@@ -42,7 +43,7 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q3_K_L.gguf) | Q3_K_L | 8.9 | |
43
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.IQ4_XS.gguf) | IQ4_XS | 8.9 | |
44
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q4_0.gguf) | Q4_0 | 9.2 | fast, low quality |
45
- | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.IQ4_NL.gguf) | IQ4_NL | 9.3 | slightly worse than Q4_K_S |
46
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q4_K_S.gguf) | Q4_K_S | 9.6 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q4_K_M.gguf) | Q4_K_M | 10.2 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q5_K_S.gguf) | Q5_K_S | 11.0 | |
@@ -50,7 +51,6 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q6_K.gguf) | Q6_K | 13.3 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q8_0.gguf) | Q8_0 | 15.9 | fast, best quality |
52
 
53
-
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56
 
 
1
  ---
2
  base_model: nicolasdec/CabraQwen14b
3
  language:
4
+ - pt
5
  - en
6
  library_name: transformers
7
  license: cc
 
43
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q3_K_L.gguf) | Q3_K_L | 8.9 | |
44
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.IQ4_XS.gguf) | IQ4_XS | 8.9 | |
45
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q4_0.gguf) | Q4_0 | 9.2 | fast, low quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.IQ4_NL.gguf) | IQ4_NL | 9.3 | prefer IQ4_XS |
47
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q4_K_S.gguf) | Q4_K_S | 9.6 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q4_K_M.gguf) | Q4_K_M | 10.2 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q5_K_S.gguf) | Q5_K_S | 11.0 | |
 
51
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q6_K.gguf) | Q6_K | 13.3 | very good quality |
52
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen14b-GGUF/resolve/main/CabraQwen14b.Q8_0.gguf) | Q8_0 | 15.9 | fast, best quality |
53
 
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56