CoolFace
Modelpublic

prithivMLmods/Ross-640-BMath-1.5B-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes247downloads
Model Card

Ross-640-BMath-1.5B-GGUF

Ross-640-BMath-1.5B is an experimental, high-precision math explanation model fine-tuned on Qwen2-1.5B, designed to provide step-by-step mathematical derivations and detailed concept explanations across a wide range of mathematical domains. It is not optimized for general reasoning or conversation, and focuses primarily on structured, non-reasoning math workflows including algebra, calculus, number theory, and combinatorics.

Model Files

File NameSizeFormatDescription
Ross-640-BMath-1.5B.F32.gguf6.18 GBF32Full precision 32-bit floating point
Ross-640-BMath-1.5B.F16.gguf3.09 GBF16Half precision 16-bit floating point
Ross-640-BMath-1.5B.BF16.gguf3.09 GBBF16Brain floating point 16-bit
Ross-640-BMath-1.5B.Q8_0.gguf1.65 GBQ8_08-bit quantized
Ross-640-BMath-1.5B.Q6_K.gguf1.27 GBQ6_K6-bit quantized
Ross-640-BMath-1.5B.Q5KM.gguf1.13 GBQ5KM5-bit quantized, medium quality
Ross-640-BMath-1.5B.Q5KS.gguf1.1 GBQ5KS5-bit quantized, small quality
Ross-640-BMath-1.5B.Q4KM.gguf986 MBQ4KM4-bit quantized, medium quality
Ross-640-BMath-1.5B.Q4KS.gguf940 MBQ4KS4-bit quantized, small quality
Ross-640-BMath-1.5B.Q3KL.gguf880 MBQ3KL3-bit quantized, large quality
Ross-640-BMath-1.5B.Q3KM.gguf824 MBQ3KM3-bit quantized, medium quality
Ross-640-BMath-1.5B.Q3KS.gguf761 MBQ3KS3-bit quantized, small quality
Ross-640-BMath-1.5B.Q2_K.gguf676 MBQ2_K2-bit quantized

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png