ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Apr 2, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled is a 3.1 billion parameter coding model, fine-tuned by ryzdfm on the Qwen2.5-Coder-3B-Instruct base. This model specializes in structured, step-by-step reasoning, distilled from Claude 4.6 Opus trajectories, and is optimized for efficient local inference on consumer hardware with as little as 4GB VRAM. It excels at code generation, math, and logic tasks, employing a distinct `` block reasoning style.

Loading preview...