ponytang3/qwen3.5-35b-a3b-opus-reasoning-distilled-v2-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": "ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2",
    "datasets": [
      "nohurry/Opus-4.6-Reasoning-3000x-filtered",
      "Jackrong/Qwen3.5-reasoning-700x",
      "Roman1111111/claude-opus-4.6-10000x"
    ],
    "tags": [
      "reasoning",
      "chain-of-thought",
      "gguf",
      "q4_k_m",
      "qwen3.5"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": "ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2",
      "datasets": [
        "nohurry/Opus-4.6-Reasoning-3000x-filtered",
        "Jackrong/Qwen3.5-reasoning-700x",
        "Roman1111111/claude-opus-4.6-10000x"
      ],
      "tags": [
        "reasoning",
        "chain-of-thought",
        "gguf",
        "q4_k_m",
        "qwen3.5"
      ]
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model: ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2\ndatasets:\n- nohurry/Opus-4.6-Reasoning-3000x-filtered\n- Jackrong/Qwen3.5-reasoning-700x\n- Roman1111111/claude-opus-4.6-10000x\ntags:\n- reasoning\n- chain-of-thought\n- gguf\n- q4_k_m\n- qwen3.5\n---\n\n# Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2-GGUF\n\n## Model Description\n\nThis is the **Q4_K_M** GGUF quantized version of [`ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2`](https://huggingface.co/ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2).\n\n### Original Model\n- **Base Model**: unsloth/Qwen3.5-35B-A3B\n- **Fine-tuned Model**: ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2\n- **Quantization**: Q4_K_M (4-bit quantization)\n\n### Training Details\n- **Method**: bf16 LoRA + response-only (train_on_responses_only)\n- **LoRA Rank**: 16\n- **Epochs**: 2\n- **Max Sequence Length**: 4096\n- **Framework**: Unsloth + TRL\n\n### Datasets\n- `nohurry/Opus-4.6-Reasoning-3000x-filtered`\n- `Jackrong/Qwen3.5-reasoning-700x`\n- `Roman1111111/claude-opus-4.6-10000x`\n\n### Usage with llama.cpp\n```bash\n./llama-cli -m model-q4_k_m.gguf -p \"Your prompt here\" -n 512\n```\n\n### Format\nThe model uses `<think>...</think>` tags for chain-of-thought reasoning.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "reasoning",
    "chain-of-thought",
    "q4_k_m",
    "qwen3.5",
    "dataset:nohurry/Opus-4.6-Reasoning-3000x-filtered",
    "dataset:Jackrong/Qwen3.5-reasoning-700x",
    "dataset:Roman1111111/claude-opus-4.6-10000x",
    "base_model:ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2",
    "base_model:quantized:ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 161,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-10T00:39:24.000Z",
  "created_at": "2026-04-10T00:32:21.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69d84515d2f62538bbfd00c1",
  "id": "ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2-GGUF",
  "modelId": "ponytang3/Qwen3.5-35B-A3B-Opus-Reasoning-Distilled-v2-GGUF",
  "sha": "67fcb6ebd081ff75a712364db8bc27223797a042",
  "createdAt": "2026-04-10T00:32:21.000Z",
  "lastModified": "2026-04-10T00:39:24.000Z",
  "author": "ponytang3",
  "downloads": 161,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 4
}