RichardErkhov/Undi95_-_Nethena-MLewd-Xwin-23B-gguf

Quantization made by Richard Erkhov.

Nethena-MLewd-Xwin-23B - GGUF

Model creator: https://huggingface.co/Undi95/
Original model: https://huggingface.co/Undi95/Nethena-MLewd-Xwin-23B/

Name	Quant method	Size
Nethena-MLewd-Xwin-23B.Q2_K.gguf	Q2_K	7.89GB
Nethena-MLewd-Xwin-23B.IQ3_XS.gguf	IQ3_XS	4.94GB
Nethena-MLewd-Xwin-23B.IQ3_S.gguf	IQ3_S	3.35GB
Nethena-MLewd-Xwin-23B.Q3_K_S.gguf	Q3_K_S	9.21GB
Nethena-MLewd-Xwin-23B.IQ3_M.gguf	IQ3_M	3.8GB
Nethena-MLewd-Xwin-23B.Q3_K.gguf	Q3_K	10.33GB
Nethena-MLewd-Xwin-23B.Q3_K_M.gguf	Q3_K_M	10.33GB
Nethena-MLewd-Xwin-23B.Q3_K_L.gguf	Q3_K_L	11.31GB
Nethena-MLewd-Xwin-23B.IQ4_XS.gguf	IQ4_XS	11.43GB
Nethena-MLewd-Xwin-23B.Q4_0.gguf	Q4_0	10.92GB
Nethena-MLewd-Xwin-23B.IQ4_NL.gguf	IQ4_NL	8.45GB
Nethena-MLewd-Xwin-23B.Q4_K_S.gguf	Q4_K_S	12.09GB
Nethena-MLewd-Xwin-23B.Q4_K.gguf	Q4_K	2.76GB
Nethena-MLewd-Xwin-23B.Q4_K_M.gguf	Q4_K_M	0.33GB
Nethena-MLewd-Xwin-23B.Q4_1.gguf	Q4_1	2.4GB
Nethena-MLewd-Xwin-23B.Q5_0.gguf	Q5_0	14.65GB
Nethena-MLewd-Xwin-23B.Q5_K_S.gguf	Q5_K_S	14.65GB
Nethena-MLewd-Xwin-23B.Q5_K.gguf	Q5_K	15.07GB
Nethena-MLewd-Xwin-23B.Q5_K_M.gguf	Q5_K_M	3.65GB
Nethena-MLewd-Xwin-23B.Q5_1.gguf	Q5_1	15.08GB
Nethena-MLewd-Xwin-23B.Q6_K.gguf	Q6_K	0.0GB
Nethena-MLewd-Xwin-23B.Q8_0.gguf	Q8_0	0.52GB

Original model description:

license: cc-by-nc-4.0 tags: - not-for-all-audiences - nsfw

Undi doing chemistry again.

Layer of Xwin-Mlewd was added in a different way than I do before, result seem good, but I'm a VRAMlet so I can only run the Q2 at 2k context for now.

Need to see if it really work good or I was just lucky with my prompt.

OG model : NeverSleep/Nethena-13B

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

LimaRP is always kicking in and thus, this can be used to have more control on the size of the output.

Thanks Ikari.