Hugging Face's logo

mradermacher
/
NeuralArjuna-7B-DT-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
yam-peleg/Experiment26-7B
Gille/StrangeMerges_32-7B-slerp
MSL7/INEX12-7b
automerger/YamShadow-7B
Kukedlc/NeuralSirKrishna-7b
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b7520c8
•
1 Parent(s): cc45a6e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -43,14 +43,13 @@ more details, including on how to concatenate multi-part files.
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
44
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
46
- | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
47
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
49
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
50
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
52
 
53
-
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
44
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
47
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
49
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
50
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/NeuralArjuna-7B-DT-GGUF/resolve/main/NeuralArjuna-7B-DT.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
52
 
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55