Hugging Face's logo

mradermacher
/
Nous-Capybara-limarpv3-34B-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
2
mradermacher commited on
Commit
0877463
•
1 Parent(s): 34fce3e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -30,9 +30,9 @@ more details, including on how to concatenate multi-part files.
30
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.6 | IQ3_XS probably better |
31
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.3 | IQ3_S probably better |
32
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.8 | IQ3_M probably better |
33
- | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.2 | almost as good as Q4_K_M |
34
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.3 | fast, medium quality |
35
- | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.0 | best weighted quant |
36
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
30
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.6 | IQ3_XS probably better |
31
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.3 | IQ3_S probably better |
32
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.8 | IQ3_M probably better |
33
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.2 | optimal size/speed/quality |
34
  | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.3 | fast, medium quality |
35
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/resolve/main/Nous-Capybara-limarpv3-34B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.0 | |
36
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant