Hugging Face's logo

mradermacher
/
Labess-7B-Instruct-GGUF

Transformers
GGUF
Tunisian Arabic
text-generation-inference
unsloth
trl
conversational
Model card Files
xet
 Community
mradermacher commited on
Commit
8c7c6c6
·
verified ·
1 Parent(s): 1424ccd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -46,9 +46,14 @@ more details, including on how to concatenate multi-part files.
46
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended |
50
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.4 | fast, recommended |
 
 
51
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q6_K.gguf) | Q6_K | 5.8 | very good quality |
 
 
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
 
46
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 3.9 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended |
51
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.4 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.0 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.1 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q6_K.gguf) | Q6_K | 5.8 | very good quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/Labess-7B-Instruct-GGUF/resolve/main/Labess-7B-Instruct.f16.gguf) | f16 | 14.1 | 16 bpw, overkill |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):