Hugging Face's logo

mradermacher
/
Ramakrishna-7b-v3-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
automerger/YamShadow-7B
Kukedlc/Neural4gsm8k
Kukedlc/NeuralSirKrishna-7b
mlabonne/NeuBeagle-7B
Kukedlc/Ramakrishna-7b
Kukedlc/NeuralGanesha-7b
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
3f4a2e7
•
1 Parent(s): 5cba379

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -44,14 +44,13 @@ more details, including on how to concatenate multi-part files.
44
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
47
- | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
48
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
53
 
54
-
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):
57
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
48
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v3-GGUF/resolve/main/Ramakrishna-7b-v3.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
53
 
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56