mannix-ita/qwen3.5-27b-omnimerge-v2-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "ManniX-ITA/Qwen3.5-27B-Omnimerge-v2",
    "tags": [
      "gguf",
      "quantized",
      "merge",
      "omnimerge-v2",
      "qwen3.5",
      "reasoning"
    ],
    "license": "apache-2.0",
    "frontmatter": {
      "base_model": "ManniX-ITA/Qwen3.5-27B-Omnimerge-v2",
      "tags": [
        "gguf",
        "quantized",
        "merge",
        "omnimerge-v2",
        "qwen3.5",
        "reasoning"
      ],
      "license": "apache-2.0"
    },
    "hero_image_url": "",
    "summary": "GGUF quantizations of ManniX-ITA/Qwen3.5-27B-Omnimerge-v2 — a 3-way weight-space merge using the **Omnimerge v2** method (OBIM + DAREx + EMR). **V2 outperforms v1 across all benchmarks, with +8 pp on GPQA Diamond reasoning and +16 pp over the best source model.**",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: ManniX-ITA/Qwen3.5-27B-Omnimerge-v2\ntags:\n  - gguf\n  - quantized\n  - merge\n  - omnimerge-v2\n  - qwen3.5\n  - reasoning\nlicense: apache-2.0\n---\n\n# Qwen3.5-27B-Omnimerge-v2-GGUF\n\nGGUF quantizations of [ManniX-ITA/Qwen3.5-27B-Omnimerge-v2](https://huggingface.co/ManniX-ITA/Qwen3.5-27B-Omnimerge-v2) — a 3-way weight-space merge using the **Omnimerge v2** method (OBIM + DAREx + EMR).\n\n**V2 outperforms v1 across all benchmarks, with +8 pp on GPQA Diamond reasoning and +16 pp over the best source model.**\n\n## Benchmark Results (Q6_K)\n\n| Benchmark | Omnimerge v1 | **Omnimerge v2** | Best source (Claude-distill) |\n|---|---|---|---|\n| **GPQA Diamond** (198q, flex) | 61.11% | **69.19% (+8.08 pp)** | 53.03% |\n| **MBPP** pass@1 | 71.80% | **74.60% (+2.80 pp)** | 71.20% |\n| **HumanEval** pass@1 | 79.88% | 79.27% (-0.61 pp) | 76.22% |\n\n## Recommended Usage\n\n```bash\nllama-server -m Qwen3.5-27B-Omnimerge-v2-Q6_K.gguf -c 32768 -ngl 99 \\\n    --reasoning-format deepseek --reasoning-budget 16384 \\\n    --temp 0.6 --top-p 0.95 --top-k 20 --dry-multiplier 0.5\n```\n\n## Source Models\n\n| Source | Weight |\n|---|---|\n| [Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled](https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled) | 0.40 |\n| [ValiantLabs/Qwen3.5-27B-Esper3.1](https://huggingface.co/ValiantLabs/Qwen3.5-27B-Esper3.1) | 0.35 |\n| [Jackrong/Qwen3.5-27B-Gemini-3.1-Pro-Reasoning-Distill](https://huggingface.co/Jackrong/Qwen3.5-27B-Gemini-3.1-Pro-Reasoning-Distill) | 0.25 |\n\nSee the [model card](https://huggingface.co/ManniX-ITA/Qwen3.5-27B-Omnimerge-v2) for full methodology.\n\n## License\n\nApache-2.0\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "quantized",
    "merge",
    "omnimerge-v2",
    "qwen3.5",
    "reasoning",
    "base_model:ManniX-ITA/Qwen3.5-27B-Omnimerge-v2",
    "base_model:quantized:ManniX-ITA/Qwen3.5-27B-Omnimerge-v2",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 703,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-13T14:24:59.000Z",
  "created_at": "2026-04-13T09:28:24.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69dcb738e307084a3a14697b",
  "id": "ManniX-ITA/Qwen3.5-27B-Omnimerge-v2-GGUF",
  "modelId": "ManniX-ITA/Qwen3.5-27B-Omnimerge-v2-GGUF",
  "sha": "8db379c01d4cb5252509c1e6fe4fe365c3a213ff",
  "createdAt": "2026-04-13T09:28:24.000Z",
  "lastModified": "2026-04-13T14:24:59.000Z",
  "author": "ManniX-ITA",
  "downloads": 703,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 17
}