RichardErkhov/zeroblu3_-_NeuralPoppy-EVO-L3-8B-gguf

Quantization made by Richard Erkhov.

NeuralPoppy-EVO-L3-8B - GGUF

Model creator: https://huggingface.co/zeroblu3/
Original model: https://huggingface.co/zeroblu3/NeuralPoppy-EVO-L3-8B/

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

Original model description:

license: llama3

A megamerge of 10 selected models merged with the "Model Stock" method, using Poppy Porpoise 0.72 as a base. Pretty good at all tasks, strong focus on RP and storytelling, uncensored (does pretty much everything if you ask it to), large knowledge base.

ST Presets in the repo.

Imatrix Quants available here https://huggingface.co/zeroblu3/NeuralPoppy-EVO-L3-imat.GGUF