Modelpublic

prithivMLmods/rStar-Coder-Qwen3-0.6B-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

1likes311downloads

Model Card

rStar-Coder-Qwen3-0.6B-GGUF

rStar-Coder-Qwen3-0.6B is a compact, multi-domain language model fine-tuned from Qwen-0.6B using the rStar-Coder dataset, which incorporates code expert clusters and an extended symbolic reasoning collection; it excels at unified reasoning across code, mathematics, and science, delivering advanced code generation, algorithm synthesis, multi-language error detection, and step-by-step scientific problem-solving, while supporting structured output in LaTeX, Markdown, JSON, CSV, and YAML—making it ideal for developers, educators, and researchers requiring efficient STEM-oriented AI on mid-range GPUs, offline clusters, and edge devices, with a focus on logic-driven responses and technical data generation rather than general chat or creative writing.

Model Files

File Name	Size	Quant Type
rStar-Coder-Qwen3-0.6B.BF16.gguf	1.2 GB	BF16
rStar-Coder-Qwen3-0.6B.F16.gguf	1.2 GB	F16
rStar-Coder-Qwen3-0.6B.F32.gguf	2.39 GB	F32
rStar-Coder-Qwen3-0.6B.Q2_K.gguf	296 MB	Q2_K
rStar-Coder-Qwen3-0.6B.Q3KL.gguf	368 MB	Q3KL
rStar-Coder-Qwen3-0.6B.Q3KM.gguf	347 MB	Q3KM
rStar-Coder-Qwen3-0.6B.Q3KS.gguf	323 MB	Q3KS
rStar-Coder-Qwen3-0.6B.Q4KM.gguf	397 MB	Q4KM
rStar-Coder-Qwen3-0.6B.Q4KS.gguf	383 MB	Q4KS
rStar-Coder-Qwen3-0.6B.Q5KM.gguf	444 MB	Q5KM
rStar-Coder-Qwen3-0.6B.Q5KS.gguf	437 MB	Q5KS
rStar-Coder-Qwen3-0.6B.Q6_K.gguf	495 MB	Q6_K
rStar-Coder-Qwen3-0.6B.Q8_0.gguf	639 MB	Q8_0

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):