Hugging Face's logo

mradermacher
/
Noro-Hermes-3x7B-GGUF

Transformers
GGUF
English
Mixture of Experts
frankenmoe
Merge
mergekit
lazymergekit
NousResearch/Nous-Hermes-2-Mistral-7B-DPO
NeverSleep/Noromaid-7B-0.4-DPO
mistralai/Mistral-7B-Instruct-v0.2
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
42a543b
•
1 Parent(s): 61ee6b5

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/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.IQ4_XS.gguf) | IQ4_XS | 10.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q4_0.gguf) | Q4_0 | 10.7 | fast, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q4_K_S.gguf) | Q4_K_S | 10.8 | fast, recommended |
46
- | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.IQ4_NL.gguf) | IQ4_NL | 10.8 | slightly worse than Q4_K_S |
47
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q4_K_M.gguf) | Q4_K_M | 11.5 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q5_K_S.gguf) | Q5_K_S | 13.0 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q5_K_M.gguf) | Q5_K_M | 13.4 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q6_K.gguf) | Q6_K | 15.4 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q8_0.gguf) | Q8_0 | 19.9 | 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/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.IQ4_XS.gguf) | IQ4_XS | 10.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q4_0.gguf) | Q4_0 | 10.7 | fast, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q4_K_S.gguf) | Q4_K_S | 10.8 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.IQ4_NL.gguf) | IQ4_NL | 10.8 | prefer IQ4_XS |
47
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q4_K_M.gguf) | Q4_K_M | 11.5 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q5_K_S.gguf) | Q5_K_S | 13.0 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q5_K_M.gguf) | Q5_K_M | 13.4 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q6_K.gguf) | Q6_K | 15.4 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Noro-Hermes-3x7B-GGUF/resolve/main/Noro-Hermes-3x7B.Q8_0.gguf) | Q8_0 | 19.9 | fast, best quality |
52
 
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55