chancyun/qwen3.5-27b-claude-4.6-opus-reasoning-distilled-gguf overview

{
  "metadata": {},
  "card_data": {
    "language": [
      "en",
      "zh"
    ],
    "license": "apache-2.0",
    "base_model": "Qwen/Qwen3.5-27B",
    "tags": [
      "unsloth",
      "qwen",
      "qwen3.5",
      "reasoning",
      "chain-of-thought",
      "Dense"
    ],
    "pipeline_tag": "image-text-to-text",
    "datasets": [
      "nohurry/Opus-4.6-Reasoning-3000x-filtered",
      "Jackrong/Qwen3.5-reasoning-700x"
    ],
    "frontmatter": {
      "language": [
        "en",
        "zh"
      ],
      "license": "apache-2.0",
      "base_model": "Qwen/Qwen3.5-27B",
      "tags": [
        "unsloth",
        "qwen",
        "qwen3.5",
        "reasoning",
        "chain-of-thought",
        "Dense"
      ],
      "pipeline_tag": "image-text-to-text",
      "datasets": [
        "nohurry/Opus-4.6-Reasoning-3000x-filtered",
        "Jackrong/Qwen3.5-reasoning-700x"
      ]
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/GHkMJL6I383eIwK1qj80K.jpeg",
    "summary": "> **Build Environment Upgrades:** > - **Fine-tuning Framework**: **Unsloth 2026.3.3** > - **Core Dependencies**: **Transformers 5.2.0** > - This model fixes the crash in the official model caused by the Jinja template not supporting the **\"developer\"** role. (commonly sent by modern coding agents like Claude Code and OpenCode) > - It does **not disable thinking mode by default**, and allowing the agent to run continuously for **over 9 minutes without interruption**. > - Compared to the original model, **autonomy and stability are significantly improved**. !HB8AleUaMAArNyM",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlanguage:\n- en\n- zh\nlicense: apache-2.0\nbase_model: Qwen/Qwen3.5-27B\ntags:\n- unsloth\n- qwen\n- qwen3.5\n- reasoning\n- chain-of-thought\n- Dense\npipeline_tag: image-text-to-text\ndatasets:\n- nohurry/Opus-4.6-Reasoning-3000x-filtered\n- Jackrong/Qwen3.5-reasoning-700x\n---\n# 🌟 Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled\n🔥 **Update (April 5):** I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process. \n\n> ❤️ Special thanks to the [**Unsloth**](https://unsloth.ai) open-source library and [@KyleHessling1](https://x.com/kylehessling1) for their support.\n\n## 📚 Resources & Guides\n\n👉 **[GitHub Repository: Jackrong-llm-finetuning-guide](https://github.com/R6410418/Jackrong-llm-finetuning-guide.git)**\nVisit the repo to dive into the codebase and reproduce the results locally or on Colab.\n\n### 📥 Core Technical Document\n**🔗 [Qwopus3.5-27b Complete Fine-Tuning Guide (PDF)](https://github.com/R6410418/Jackrong-llm-finetuning-guide/blob/main/guidePDF/Qwopus3-5-27b-Colab_complete_guide_to_llm_finetuning.pdf)**\n* **The Full Pipeline:** A step-by-step walkthrough—from downloading the base model and unifying heterogeneous data, to configuring trainer hyperparameters and publishing to Hugging Face.\n* **Beginner Friendly:** Includes an introductory guide to getting started with Google Colab and Unsloth.\n* *Feedback welcome! If you spot any areas for improvement, please let me know and I will update it promptly.*\n\n> **A Note:**\n> My goal isn't just to detail a workflow, but to demystify LLM training. Beyond the social media hype, fine-tuning isn't an unattainable ritual—often, all you need is a Google account, a standard laptop, and relentless curiosity. \n> \n> *No one starts as an expert, but every expert was once brave enough to begin.*\n> \n> All training and testing for this project were self-funded. If you find this model or guide helpful, a **Star ⭐️ on GitHub** would be the greatest encouragement. Thank you! 🙏\n\n> [!Note]\n> The Claude series model optimizations are named under the **Qwopus3.5 series**, with the latest version being **🌟Qwopus3.5-v3**.\n\n---\n# 🌟 Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled\n\n> **Build Environment Upgrades:**\n> - **Fine-tuning Framework**: **Unsloth 2026.3.3** \n> - **Core Dependencies**: **Transformers 5.2.0**\n> - This model fixes the crash in the official model caused by the Jinja template not supporting the **\"developer\"** role. (commonly sent by modern coding agents like Claude Code and OpenCode)\n> - It does **not disable thinking mode by default**, and allowing the agent to run continuously for **over 9 minutes without interruption**.\n> - Compared to the original model, **autonomy and stability are significantly improved**.\n\n![HB8AleUaMAArNyM](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/GHkMJL6I383eIwK1qj80K.jpeg)\n\n\n## 💡 Model Introduction\n**Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled** is a highly capable reasoning model fine-tuned on top of the powerful Qwen3.5 architecture. The model's core directive is to leverage state-of-the-art Chain-of-Thought (CoT) distillation primarily sourced from Claude-4.6 Opus interactions. \n\nThrough Supervised Fine-Tuning (SFT) focusing specifically on structured reasoning logic, this model excels in breaking down complex user problems, planning step-by-step methodologies within strictly formatted `<think>` tags, and ultimately delivering precise, nuanced solutions. \n\n### 🧠 Example of Learned Reasoning Scaffold（Example）\n\nThe model includes targeted optimizations addressing Qwen3.5’s tendency toward excessive transitional or repetitive reasoning on simple queries. Through deep distillation and structural imitation of Claude-4.6-Opus reasoning chains, the model adopts a more efficient structured thinking pattern:  \n**“Let me analyze this request carefully: 1..2..3...”.**  \nThis streamlined reasoning paradigm significantly reduces redundant cognitive loops while preserving deep analytical capacity, resulting in substantially improved inference efficiency.\n\n```text\nLet me analyze this request carefully:\n\n1. Identify the core objective of the problem.\n2. Break the task into clearly defined subcomponents.\n3. Evaluate constraints and edge cases.\n4. Formulate a step-by-step solution plan.\n5. Execute the reasoning sequentially and verify consistency.\n            .\n            .\n            .\n```\n\n---\n\n## 🗺️ Training Pipeline Overview\n\n```text\nBase Model (Qwen3.5-27B)\n │\n ▼\nSupervised Fine-Tuning (SFT) + LoRA\n │\n ▼\nFinal Model (Claude-4.6-Opus-Reasoning-Distilled,text-only)\n```\n\n## 📋 Stage Details\n\n**🔧Tool Calling Benchmark**（benchmark tests by user @Chris Klaus）\n\n![Screenshot 2026-03-24 at 10.19.28 AM](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/TjfbXq5AahoMj8xZuFDig.png)\n\n> **From the test results, it is clear that different Qwen3.5 quantized models show significant differences in tool-calling capability. Among them, only the 27B model distilled with Claude Opus reasoning demonstrates stable performance.**\n\n---\n\n🔥**Community-tested advantages** (benchmark tests by user @sudoing on a single RTX 3090):\n\nQwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled shows significant advantages in coding-agent environments such as Claude Code and OpenCode:\n\n>- **Native support for the “developer” role**, requiring no Jinja template patches or ChatML workarounds.  \n>- **Thinking mode fully preserved** (logs confirm `thinking=1`), not silently disabled, maintaining the complete chain-of-thought reasoning process.  \n>- **Greatly improved autonomy and stability** — capable of running continuously for **over 9 minutes autonomously** (with zero human intervention). It actively waits for tool responses, reads outputs, self-corrects errors, and can even automatically generate a README, whereas the base model often stalls or freezes mid-execution.  \n\n>**Hardware usage remains unchanged:**  \n>- About **16.5 GB VRAM** with **Q4_K_M** quantization  \n>- **29–35 tok/s** generation speed  \n>- **Full 262K context** with no compromises  \n\n- These improvements come from successfully distilling the **structured reasoning style of Claude 4.6 Opus**, allowing Qwopus to be truly **plug-and-play in modern local coding agents** and deliver an experience close to Opus in smoothness and usability.\n\n\n---\n\n### 🔹 Supervised Fine-Tuning (SFT)\n- **Objective:** To inject high-density reasoning logic and establish a strict format for problem-solving involving an internal thinking state prior to outputting the final response.\n- **Methodology:** We utilized **Unsloth** for highly efficient memory and compute optimization. A critical component of this stage is the `train_on_responses_only` strategy, masking instructions so the loss is purely calculated over the generation of the `<think>` sequences and the subsequent solutions. \n- **Format Enforcement:** All training samples were systematically normalized so the model strictly abides by the structure `<think> {internal reasoning} </think>\\n {final answer}`.\n\n### 📚 All Datasets Used\nThe dataset consists of high-quality, filtered reasoning distillation data:\n\n| Dataset Name | Description / Purpose |\n|--------------|-----------------------|\n| [nohurry/Opus-4.6-Reasoning-3000x-filtered](https://huggingface.co/datasets/nohurry/Opus-4.6-Reasoning-3000x-filtered) | Provides comprehensive Claude 4.6 Opus reasoning trajectories. |\n| [Jackrong/Qwen3.5-reasoning-700x](https://huggingface.co/datasets/Jackrong/Qwen3.5-reasoning-700x) | Additional curated reasoning samples designed to strengthen structured step-by-step problem solving and improve reasoning diversity. |\n\n## 🌟 Core Skills & Capabilities\n1. **Modular & Structured Thinking:** Inheriting traits from Opus-level reasoning, the model demonstrates confident parsing of the prompt, establishing an outlined plan in its `<think>` block sequentially rather than exploratory \"trial-and-error\" self-doubt.\n\n## ⚠️ Limitations & Intended Use\n- **Hallucination Risk:** While reasoning is strong, the model remains an autoregressive LLM; external facts provided during the thinking sequence may occasionally contain hallucinations if verifying real-world events.\n- **Intended Scenario:** Best suited for offline analytical tasks, coding, math, and heavy logic-dependent prompting where the user needs to transparently follow the AI's internal logic.\n- **Preview Version Notice:** Because this model is relatively new and intentionally lightweight, the surrounding ecosystem — including inference templates, fine-tuning pipelines, routing configurations, and tooling integrations — may not yet be fully mature or standardized. As a result, users may encounter occasional bugs, compatibility inconsistencies, or integration edge cases. The current release should be considered a preview build while the broader architectural stack and supporting utilities continue to stabilize and improve.\n\n## 🙏 Acknowledgements\nSignificant thanks to the [Unsloth AI](https://unsloth.ai/) team for making rapid fine-tuning of MoE and large LLM models accessible. Additionally, we acknowledge Qwen internally, and the open-source community developers producing exceptional distilled datasets (`nohurry` and `TeichAI`).\n\n## 📖 Citation\n\nIf you use this model in your research or projects, please cite:\n\n```bibtex\n@misc{jackrong_qwen35_opus_distilled,\n  title        = {Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled},\n  author       = {Jackrong},\n  year         = {2026},\n  publisher    = {Hugging Face},\n  howpublished = {\\url{https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled}}\n}\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "qwen3_5",
    "unsloth",
    "qwen",
    "qwen3.5",
    "reasoning",
    "chain-of-thought",
    "Dense",
    "image-text-to-text",
    "en",
    "zh",
    "dataset:nohurry/Opus-4.6-Reasoning-3000x-filtered",
    "dataset:Jackrong/Qwen3.5-reasoning-700x",
    "base_model:Qwen/Qwen3.5-27B",
    "base_model:quantized:Qwen/Qwen3.5-27B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 765,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-15T12:31:43.000Z",
  "created_at": "2026-04-15T12:31:42.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}

{
  "_id": "69df852ec0abeed6182bf44b",
  "id": "chancyun/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
  "modelId": "chancyun/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
  "sha": "9f19e3747ab0903b4ed4d03d753b9fd8e96a1111",
  "createdAt": "2026-04-15T12:31:42.000Z",
  "lastModified": "2026-04-15T12:31:43.000Z",
  "author": "chancyun",
  "downloads": 765,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 10
}