Modelpublic

RichardErkhov/MARIO-Math-Reasoning_-_AlphaMath-7B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes236downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

AlphaMath-7B - GGUF

—Model creator: https://huggingface.co/MARIO-Math-Reasoning/
—Original model: https://huggingface.co/MARIO-Math-Reasoning/AlphaMath-7B/

Name	Quant method	Size
AlphaMath-7B.Q2_K.gguf	Q2_K	2.53GB
AlphaMath-7B.IQ3_XS.gguf	IQ3_XS	2.79GB
AlphaMath-7B.IQ3_S.gguf	IQ3_S	2.92GB
AlphaMath-7B.Q3_K_S.gguf	Q3KS	2.92GB
AlphaMath-7B.IQ3_M.gguf	IQ3_M	3.06GB
AlphaMath-7B.Q3_K.gguf	Q3_K	3.22GB
AlphaMath-7B.Q3_K_M.gguf	Q3KM	3.22GB
AlphaMath-7B.Q3_K_L.gguf	Q3KL	3.49GB
AlphaMath-7B.IQ4_XS.gguf	IQ4_XS	3.56GB
AlphaMath-7B.Q4_0.gguf	Q4_0	3.73GB
AlphaMath-7B.IQ4_NL.gguf	IQ4_NL	3.74GB
AlphaMath-7B.Q4_K_S.gguf	Q4KS	3.75GB
AlphaMath-7B.Q4_K.gguf	Q4_K	3.93GB
AlphaMath-7B.Q4_K_M.gguf	Q4KM	3.93GB
AlphaMath-7B.Q4_1.gguf	Q4_1	4.1GB
AlphaMath-7B.Q5_0.gguf	Q5_0	4.48GB
AlphaMath-7B.Q5_K_S.gguf	Q5KS	4.48GB
AlphaMath-7B.Q5_K.gguf	Q5_K	4.59GB
AlphaMath-7B.Q5_K_M.gguf	Q5KM	4.59GB
AlphaMath-7B.Q5_1.gguf	Q5_1	4.86GB
AlphaMath-7B.Q6_K.gguf	Q6_K	5.28GB
AlphaMath-7B.Q8_0.gguf	Q8_0	6.84GB

Original model description: --- license: mit --- AlphaMath-7B based on DeepSeek-Math-base-7B