Hugging Face's logo

mradermacher
/
PATH-14B-COT-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
qwen2
trl
sft
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
4fc0425
·
verified ·
1 Parent(s): 70629bd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -40,9 +40,13 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
41
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
 
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
 
40
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
41
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
48
  | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/PATH-14B-COT-GGUF/resolve/main/PATH-14B-COT.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):