🌟 QwOpus-4.6-Coder-3B — Claude Opus 4.6 Reasoning Distilled

(a.k.a. qwen2.5-coder-3b-claude_opus_4.6-distilled)

A compact, fast, locally-runnable coding model fine-tuned on top of Qwen2.5-Coder-3B-Instruct using high-quality reasoning trajectories distilled from Claude 4.6 Opus. Designed to run efficiently on consumer hardware with as little as 4GB VRAM at ~88 tokens/sec.

💡 Model Introduction

QwOpus-4.6-Coder-3B (full name: Qwen2.5-Coder-3B-Claude-Opus-4.6-Distilled) combines the strong code generation foundation of Qwen2.5-Coder with the structured, step-by-step reasoning style of Claude 4.6 Opus. Through Supervised Fine-Tuning (SFT) with LoRA, the model learns to think through problems carefully inside <think> tags before delivering precise, well-structured answers.

Unlike larger distilled models, this 3B model is built for real local inference — fast, private, and fits comfortably in 4GB VRAM.

Naming note: QwOpus is the short, spoken name for this model (Qw = Qwen, Opus = Claude Opus). The Hugging Face repo and file names use the longer, fully descriptive qwen2.5-coder-3b-claude_opus_4.6-distilled for clarity and searchability. Both refer to the same model.

🧠 Reasoning Style

The model adopts Claude Opus's structured reasoning pattern:

<think>
Let me analyze this carefully.

1. Identify the core objective.
2. Break down into subcomponents.
3. Consider edge cases and constraints.
4. Formulate and verify the solution.
</think>

[Final clean answer here]

🗺️ Training Pipeline

Base Model (Qwen/Qwen2.5-Coder-3B-Instruct)
 │
 ▼
Supervised Fine-Tuning (SFT) + LoRA (r=16)
 │  • 3,209 high-quality Claude reasoning samples
 │  • Unsloth 2x faster training
 │  • 1 epoch on T4 GPU (~46 mins)
 │  • Final loss: 0.88
 ▼
QwOpus-4.6-Coder-3B
(qwen2.5-coder-3b-claude_opus_4.6-distilled)

📋 Training Details

📚 Datasets Used

🚀 Running Locally

Via Ollama (easiest)

ollama run hf.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled

Via llama.cpp (for GPU acceleration)

./llama-cli.exe \
  -m qwen2.5-coder-3b-claude_opus_4.6-distilled.Q4_K_M.gguf \
  -ngl 99 \
  --flash-attn on \
  --jinja \
  -cnv \
  --repeat-penalty 1.1 \
  -p "You are a helpful assistant that thinks step by step."

Tip: feel free to rename your local .gguf file to qwopus-4.6-coder-3b.Q4_K_M.gguf if you prefer the short name day-to-day — it's the same weights either way.

🌟 Core Capabilities

• Structured Reasoning — thinks through problems step by step in <think> blocks before answering
• Code Generation — built on Qwen2.5-Coder, strong at Python, JavaScript, algorithms
• Math & Logic — correctly solves multi-step problems with verification
• Fast Local Inference — 88 t/s on RTX 3050 4GB, fully GPU-accelerated

⚡ Hardware Requirements

Runs comfortably on 4GB VRAM laptops and desktops.

⚠️ Limitations

• 3B scale — will struggle with very long multi-file code generation or complex system design
• 1 epoch training — reasoning style is distilled but not as deep as larger models
• Hallucination risk — like all LLMs, may produce incorrect facts; always verify outputs

🙏 Acknowledgements

• Unsloth AI for making fine-tuning accessible on consumer hardware
• nohurry, TeichAI, and Jackrong for the high-quality distillation datasets
• Qwen team for the excellent Qwen2.5-Coder base model

📖 Citation

@misc{ryzdfm_qwopus_4_6_coder_3b,
  title        = {QwOpus-4.6-Coder-3B (Qwen2.5-Coder-3B Claude Opus 4.6 Reasoning Distilled)},
  author       = {ryzdfm},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled}}
}