Hugging Face's logo

mradermacher
/
Magistral-Small-2506-abliterated-GGUF

Transformers
GGUF
chat
abliterated
uncensored
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
8bbdbb5
·
verified ·
1 Parent(s): 6b7a7cf

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -69,8 +69,13 @@ more details, including on how to concatenate multi-part files.
69
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q3_K_S.gguf) | Q3_K_S | 10.5 | |
70
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q3_K_M.gguf) | Q3_K_M | 11.6 | lower quality |
71
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q3_K_L.gguf) | Q3_K_L | 12.5 | |
 
72
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q4_K_S.gguf) | Q4_K_S | 13.6 | fast, recommended |
73
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q4_K_M.gguf) | Q4_K_M | 14.4 | fast, recommended |
 
 
 
 
74
 
75
  Here is a handy graph by ikawrakow comparing some lower-quality quant
76
  types (lower is better):
 
69
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q3_K_S.gguf) | Q3_K_S | 10.5 | |
70
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q3_K_M.gguf) | Q3_K_M | 11.6 | lower quality |
71
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q3_K_L.gguf) | Q3_K_L | 12.5 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.IQ4_XS.gguf) | IQ4_XS | 13.0 | |
73
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q4_K_S.gguf) | Q4_K_S | 13.6 | fast, recommended |
74
  | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q4_K_M.gguf) | Q4_K_M | 14.4 | fast, recommended |
75
+ | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q5_K_S.gguf) | Q5_K_S | 16.4 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q5_K_M.gguf) | Q5_K_M | 16.9 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q6_K.gguf) | Q6_K | 19.4 | very good quality |
78
+ | [GGUF](https://huggingface.co/mradermacher/Magistral-Small-2506-abliterated-GGUF/resolve/main/Magistral-Small-2506-abliterated.Q8_0.gguf) | Q8_0 | 25.2 | fast, best quality |
79
 
80
  Here is a handy graph by ikawrakow comparing some lower-quality quant
81
  types (lower is better):