prithivmlmods/sage-mm-qwen3-vl-4b-sft-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "base_model": [
      "allenai/SAGE-MM-Qwen3-VL-4B-SFT"
    ],
    "pipeline_tag": "video-text-to-text",
    "library_name": "transformers",
    "tags": [
      "text-generation-inference",
      "llama.cpp"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "base_model": [
        "allenai/SAGE-MM-Qwen3-VL-4B-SFT"
      ],
      "pipeline_tag": "video-text-to-text",
      "library_name": "transformers",
      "tags": [
        "text-generation-inference",
        "llama.cpp"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "> The SAGE-MM-Qwen3-VL-4B-SFT from allenai is a 4B-parameter vision-language model fine-tuned from Qwen/Qwen3-VL-4B-Instruct, serving as the core decision-maker in the SAGE (Smart Any-Horizon Agent) system for long video reasoning, operating in two stages: Stage-1 analyzes initial sampled frames and metadata to classify queries as single-turn (immediate answer) or multi-turn (tool-required), while Stage-2 iteratively calls tools, processes observations, and refines context until resolution. It generates JSON-formatted actions for specialized tools like web-search (external knowledge), transcribe-speech (ASR on timestamps), ground-event (temporal localization), extract-video-parts (high-res frames/subclips), and analyze (detailed visual breakdown), enabling robust handling of extended videos beyond fixed horizons via dynamic tool orchestration. Released under Apache 2.0 for research/educational use per Ai2 guidelines, it requires the SAGE GitHub runtime for tool execution/parsing and supports GGUF quantizations for efficient deployment, excelling in video Q&A across sports, narratives, and events.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\nbase_model:\n- allenai/SAGE-MM-Qwen3-VL-4B-SFT\npipeline_tag: video-text-to-text\nlibrary_name: transformers\ntags:\n- text-generation-inference\n- llama.cpp\n---\n\n# **SAGE-MM-Qwen3-VL-4B-SFT-GGUF**\n\n> The SAGE-MM-Qwen3-VL-4B-SFT from allenai is a 4B-parameter vision-language model fine-tuned from Qwen/Qwen3-VL-4B-Instruct, serving as the core decision-maker in the SAGE (Smart Any-Horizon Agent) system for long video reasoning, operating in two stages: Stage-1 analyzes initial sampled frames and metadata to classify queries as single-turn (immediate answer) or multi-turn (tool-required), while Stage-2 iteratively calls tools, processes observations, and refines context until resolution. It generates JSON-formatted actions for specialized tools like web-search (external knowledge), transcribe-speech (ASR on timestamps), ground-event (temporal localization), extract-video-parts (high-res frames/subclips), and analyze (detailed visual breakdown), enabling robust handling of extended videos beyond fixed horizons via dynamic tool orchestration. Released under Apache 2.0 for research/educational use per Ai2 guidelines, it requires the SAGE GitHub runtime for tool execution/parsing and supports GGUF quantizations for efficient deployment, excelling in video Q&A across sports, narratives, and events.\n\n## SAGE-MM-Qwen3-VL-4B-SFT [GGUF]\n\n| File Name | Quant Type | File Size | File Link |\n| - | - | - | - |\n| SAGE-MM-Qwen3-VL-4B-SFT.IQ4_XS.gguf | IQ4_XS | 2.49 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.IQ4_XS.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q2_K.gguf | Q2_K | 1.8 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q2_K.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q3_K_L.gguf | Q3_K_L | 2.41 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q3_K_L.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q3_K_M.gguf | Q3_K_M | 2.24 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q3_K_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q3_K_S.gguf | Q3_K_S | 2.05 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q3_K_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q4_K_M.gguf | Q4_K_M | 2.72 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q4_K_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q4_K_S.gguf | Q4_K_S | 2.6 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q4_K_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q5_K_M.gguf | Q5_K_M | 3.16 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q5_K_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q5_K_S.gguf | Q5_K_S | 3.09 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q5_K_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q6_K.gguf | Q6_K | 3.63 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q6_K.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.Q8_0.gguf | Q8_0 | 4.69 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.Q8_0.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.f16.gguf | F16 | 8.83 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.f16.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ1_M.gguf | i1-IQ1_M | 1.25 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ1_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ1_S.gguf | i1-IQ1_S | 1.18 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ1_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_M.gguf | i1-IQ2_M | 1.68 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_S.gguf | i1-IQ2_S | 1.58 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_XS.gguf | i1-IQ2_XS | 1.48 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_XS.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_XXS.gguf | i1-IQ2_XXS | 1.37 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ2_XXS.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_M.gguf | i1-IQ3_M | 2.13 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_S.gguf | i1-IQ3_S | 2.07 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_XS.gguf | i1-IQ3_XS | 1.98 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_XS.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_XXS.gguf | i1-IQ3_XXS | 1.84 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ3_XXS.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ4_NL.gguf | i1-IQ4_NL | 2.6 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ4_NL.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ4_XS.gguf | i1-IQ4_XS | 2.48 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-IQ4_XS.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q2_K.gguf | i1-Q2_K | 1.8 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q2_K.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q2_K_S.gguf | i1-Q2_K_S | 1.69 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q2_K_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q3_K_L.gguf | i1-Q3_K_L | 2.41 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q3_K_L.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q3_K_M.gguf | i1-Q3_K_M | 2.24 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q3_K_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q3_K_S.gguf | i1-Q3_K_S | 2.05 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q3_K_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_0.gguf | i1-Q4_0 | 2.59 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_0.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_1.gguf | i1-Q4_1 | 2.84 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_1.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_K_M.gguf | i1-Q4_K_M | 2.72 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_K_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_K_S.gguf | i1-Q4_K_S | 2.6 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q4_K_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q5_K_M.gguf | i1-Q5_K_M | 3.16 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q5_K_M.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q5_K_S.gguf | i1-Q5_K_S | 3.09 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q5_K_S.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.i1-Q6_K.gguf | i1-Q6_K | 3.63 GB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.i1-Q6_K.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.imatrix.gguf | imatrix | 3.87 MB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.imatrix.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.mmproj-Q8_0.gguf | mmproj-Q8_0 | 454 MB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.mmproj-Q8_0.gguf) |\n| SAGE-MM-Qwen3-VL-4B-SFT.mmproj-f16.gguf | mmproj-f16 | 836 MB | [Download](https://huggingface.co/prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF/blob/main/SAGE-MM-Qwen3-VL-4B-SFT.mmproj-f16.gguf) |\n\n## Quants Usage \n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "qwen3_vl",
    "text-generation-inference",
    "llama.cpp",
    "video-text-to-text",
    "en",
    "base_model:allenai/SAGE-MM-Qwen3-VL-4B-SFT",
    "base_model:quantized:allenai/SAGE-MM-Qwen3-VL-4B-SFT",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 107,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-20T04:58:42.000Z",
  "created_at": "2025-12-18T04:13:06.000Z",
  "pipeline_tag": "video-text-to-text",
  "library_name": "transformers"
}

{
  "_id": "69437f529e1d4632faef7ab9",
  "id": "prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF",
  "modelId": "prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-GGUF",
  "sha": "55c0fa671a7c58a403241f8860dad5431c23c406",
  "createdAt": "2025-12-18T04:13:06.000Z",
  "lastModified": "2025-12-20T04:58:42.000Z",
  "author": "prithivMLmods",
  "downloads": 107,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "video-text-to-text",
  "library_name": "transformers",
  "siblings_count": 42
}