Hugging Face's logo

mradermacher
/
Qwen2.5-14B-CIC-SciCite-GGUF

Transformers
GGUF
English
scientometrics
citation_analysis
citation_intent_classification
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
e454cb9
·
verified ·
1 Parent(s): 8c11831

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -31,7 +31,14 @@ more details, including on how to concatenate multi-part files.
31
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q2_K.gguf) | Q2_K | 5.9 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
 
 
 
 
 
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
37
  types (lower is better):
 
31
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q2_K.gguf) | Q2_K | 5.9 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
34
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
37
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-CIC-SciCite-GGUF/resolve/main/Qwen2.5-14B-CIC-SciCite.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):