Cerium-Qwen3-R1-Dev-GGUF

Cerium-Qwen3-R1-Dev is a high-efficiency, multi-domain model fine-tuned on Qwen-0.6B using the rStar-Coder dataset, enhanced with code expert clusters, an extended open code reasoning dataset, and DeepSeek R1 coding sample traces. 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
Cerium-Qwen3-R1-Dev.BF16.gguf	BF16	1.2 GB
Cerium-Qwen3-R1-Dev.F16.gguf	F16	1.2 GB
Cerium-Qwen3-R1-Dev.F32.gguf	F32	2.39 GB
Cerium-Qwen3-R1-Dev.Q2_K.gguf	Q2_K	296 MB
Cerium-Qwen3-R1-Dev.Q3_K_L.gguf	Q3_K_L	368 MB
Cerium-Qwen3-R1-Dev.Q3_K_M.gguf	Q3_K_M	347 MB
Cerium-Qwen3-R1-Dev.Q3_K_S.gguf	Q3_K_S	323 MB
Cerium-Qwen3-R1-Dev.Q4_K_M.gguf	Q4_K_M	397 MB
Cerium-Qwen3-R1-Dev.Q4_K_S.gguf	Q4_K_S	383 MB
Cerium-Qwen3-R1-Dev.Q5_K_M.gguf	Q5_K_M	444 MB
Cerium-Qwen3-R1-Dev.Q5_K_S.gguf	Q5_K_S	437 MB
Cerium-Qwen3-R1-Dev.Q6_K.gguf	Q6_K	495 MB
Cerium-Qwen3-R1-Dev.Q8_0.gguf	Q8_0	639 MB

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):