Hugging Face's logo

knifeayumu
/
Lite-Cydonia-22B-v1.1-50-50-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community

Llamacpp Quantizations of knifeayumu/Lite-Cydonia-22B-v1.1-50-50

Using llama.cpp release b3837 for quantization.

Original model: knifeayumu/Lite-Cydonia-22B-v1.1-50-50

Quant Types:

Filename Quant type File Size
Lite-Cydonia-22B-v1.1-50-50-F16.gguf F16 41.4GB
Lite-Cydonia-22B-v1.1-50-50-Q8_0.gguf Q8_0 22.0GB
Lite-Cydonia-22B-v1.1-50-50-Q6_K.gguf Q6_K 16.9GB
Lite-Cydonia-22B-v1.1-50-50-Q5_K_M.gguf Q5_K_M 14.6GB
Lite-Cydonia-22B-v1.1-50-50-Q5_K_S.gguf Q5_K_S 14.2GB
Lite-Cydonia-22B-v1.1-50-50-Q4_K_M.gguf Q4_K_M 12.4GB
Lite-Cydonia-22B-v1.1-50-50-Q4_K_S.gguf Q4_K_S 11.7GB
Lite-Cydonia-22B-v1.1-50-50-Q3_K_L.gguf Q3_K_L 10.9GB
Lite-Cydonia-22B-v1.1-50-50-Q3_K_M.gguf Q3_K_M 10.0GB
Lite-Cydonia-22B-v1.1-50-50-Q3_K_S.gguf Q3_K_S 8.97GB
Lite-Cydonia-22B-v1.1-50-50-Q2_K.gguf Q2_K 7.70GB
Downloads last month
51
GGUF
Model size
22.2B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for knifeayumu/Lite-Cydonia-22B-v1.1-50-50-GGUF

Base model

knifeayumu/Lite-Cydonia-22B-v1.1-50-50
Quantized
(3)
this model

Collection including knifeayumu/Lite-Cydonia-22B-v1.1-50-50-GGUF