RichardErkhov/Nitral-AI_-_Poppy_Porpoise-0.72-L3-8B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Poppy_Porpoise-0.72-L3-8B - GGUF

• Model creator: https://huggingface.co/Nitral-AI/
• Original model: https://huggingface.co/Nitral-AI/Poppy_Porpoise-0.72-L3-8B/

Name	Quant method	Size
Poppy_Porpoise-0.72-L3-8B.Q2_K.gguf	Q2_K	2.96GB
Poppy_Porpoise-0.72-L3-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Poppy_Porpoise-0.72-L3-8B.IQ3_S.gguf	IQ3_S	3.43GB
Poppy_Porpoise-0.72-L3-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Poppy_Porpoise-0.72-L3-8B.IQ3_M.gguf	IQ3_M	3.52GB
Poppy_Porpoise-0.72-L3-8B.Q3_K.gguf	Q3_K	3.74GB
Poppy_Porpoise-0.72-L3-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Poppy_Porpoise-0.72-L3-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Poppy_Porpoise-0.72-L3-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Poppy_Porpoise-0.72-L3-8B.Q4_0.gguf	Q4_0	4.34GB
Poppy_Porpoise-0.72-L3-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Poppy_Porpoise-0.72-L3-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Poppy_Porpoise-0.72-L3-8B.Q4_K.gguf	Q4_K	4.58GB
Poppy_Porpoise-0.72-L3-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Poppy_Porpoise-0.72-L3-8B.Q4_1.gguf	Q4_1	4.78GB
Poppy_Porpoise-0.72-L3-8B.Q5_0.gguf	Q5_0	5.21GB
Poppy_Porpoise-0.72-L3-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Poppy_Porpoise-0.72-L3-8B.Q5_K.gguf	Q5_K	5.34GB
Poppy_Porpoise-0.72-L3-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Poppy_Porpoise-0.72-L3-8B.Q5_1.gguf	Q5_1	5.65GB
Poppy_Porpoise-0.72-L3-8B.Q6_K.gguf	Q6_K	6.14GB
Poppy_Porpoise-0.72-L3-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: - Nitral-AI/PP_0.71b - Nitral-AI/PP_0.71a library_name: transformers tags: - mergekit - merge license: other

"Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences.

Quants Available From Lewdiculus: https://huggingface.co/Lewdiculous/Poppy_Porpoise-0.72-L3-8B-GGUF-IQ-Imatrix

Recomended ST Presets:(Updated for 0.72) Porpoise Presets

If you want to use vision functionality:

• You must use the latest versions of Koboldcpp.

To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo. Llava MMProj

• You can load the mmproj by using the corresponding section in the interface: