Transformers
GGUF
English
Inference Endpoints
mradermacher commited on
Commit
b8531c5
1 Parent(s): 8b9aa1e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -36,14 +36,13 @@ more details, including on how to concatenate multi-part files.
36
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
39
- | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
40
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
45
 
46
-
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
49
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
40
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Mistral-v2-orpo-GGUF/resolve/main/Mistral-v2-orpo.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
45
 
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
48