Modelpublic

prithivMLmods/Gacrux-R1-Qwen3-1.7B-MoD-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

0likes334downloads

Model Card

Gacrux-R1-Qwen3-1.7B-MoD-GGUF

Gacrux-R1-Qwen3-1.7B-MoD is a high-efficiency, multi-domain model fine-tuned on Qwen3-1.7B with traces of Mixture of Domains (MoD). It leverages the prithivMLmods/Gargantua-R1-Wee dataset, designed for rigorous mathematical problem-solving and enriched with multi-domain coverage across mathematics, coding, and science. This model blends symbolic precision, scientific logic, and structured output fluency—making it an ideal tool for developers, educators, and researchers seeking advanced reasoning under constrained compute.

Model Files

File Name	Quant Type	File Size
Gacrux-R1-Qwen3-1.7B-MoD.BF16.gguf	BF16	3.45 GB
Gacrux-R1-Qwen3-1.7B-MoD.F16.gguf	F16	3.45 GB
Gacrux-R1-Qwen3-1.7B-MoD.F32.gguf	F32	6.89 GB
Gacrux-R1-Qwen3-1.7B-MoD.Q2_K.gguf	Q2_K	778 MB
Gacrux-R1-Qwen3-1.7B-MoD.Q3KL.gguf	Q3KL	1 GB
Gacrux-R1-Qwen3-1.7B-MoD.Q3KM.gguf	Q3KM	940 MB
Gacrux-R1-Qwen3-1.7B-MoD.Q3KS.gguf	Q3KS	867 MB
Gacrux-R1-Qwen3-1.7B-MoD.Q4KM.gguf	Q4KM	1.11 GB
Gacrux-R1-Qwen3-1.7B-MoD.Q4KS.gguf	Q4KS	1.06 GB
Gacrux-R1-Qwen3-1.7B-MoD.Q5KM.gguf	Q5KM	1.26 GB
Gacrux-R1-Qwen3-1.7B-MoD.Q5KS.gguf	Q5KS	1.23 GB
Gacrux-R1-Qwen3-1.7B-MoD.Q6_K.gguf	Q6_K	1.42 GB
Gacrux-R1-Qwen3-1.7B-MoD.Q8_0.gguf	Q8_0	1.83 GB

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):