ggml-org/qwen2.5-omni-7b-gguf Q4_K_M GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
ggml-org/qwen2.5-omni-7b-gguf overview
Original model: https://huggingface.co/Qwen/Qwen2.5-Omni-7B Modalities: Ref PR: https://github.com/ggml-org/llama.cpp/pull/13784
Downloads
633
Likes
22
Pipeline
any-to-any
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
5 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen2.5-Omni-7B-Q4_K_M.gguf | GGUF | Q4_K_M | 4.36 GB | Download |
| Qwen2.5-Omni-7B-Q8_0.gguf | GGUF | — | 7.54 GB | Download |
| Qwen2.5-Omni-7B-f16.gguf | GGUF | F16 | 14.19 GB | Download |
| mmproj-Qwen2.5-Omni-7B-Q8_0.gguf | GGUF | — | 1.44 GB | Download |
| mmproj-Qwen2.5-Omni-7B-f16.gguf | GGUF | F16 | 2.46 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "other",
"license_name": "qwen-research",
"license_link": "https://huggingface.co/Qwen/Qwen2.5-Omni-7B/blob/main/LICENSE",
"language": [
"en"
],
"tags": [
"multimodal"
],
"pipeline_tag": "any-to-any",
"base_model": [
"Qwen/Qwen2.5-Omni-7B"
],
"frontmatter": {
"license": "other",
"license_name": "qwen-research",
"license_link": "https://huggingface.co/Qwen/Qwen2.5-Omni-7B/blob/main/LICENSE",
"language": [
"en"
],
"tags": [
"multimodal"
],
"pipeline_tag": "any-to-any",
"base_model": [
"Qwen/Qwen2.5-Omni-7B"
]
},
"hero_image_url": "",
"summary": "Original model: https://huggingface.co/Qwen/Qwen2.5-Omni-7B Modalities: Ref PR: https://github.com/ggml-org/llama.cpp/pull/13784",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: other\nlicense_name: qwen-research\nlicense_link: https://huggingface.co/Qwen/Qwen2.5-Omni-7B/blob/main/LICENSE\nlanguage:\n- en\ntags:\n- multimodal\npipeline_tag: any-to-any\nbase_model:\n- Qwen/Qwen2.5-Omni-7B\n---\n\n# Qwen2.5-Omni-7B-GGUF\n\nOriginal model: https://huggingface.co/Qwen/Qwen2.5-Omni-7B\n\nModalities:\n- ✅ Text input\n- ✅ Audio input\n- ✅ Image input\n- ❌ Video input\n- ❌ Audio generation\n\nRef PR: https://github.com/ggml-org/llama.cpp/pull/13784\n",
"related_quantizations": []
},
"tags": [
"gguf",
"multimodal",
"any-to-any",
"en",
"base_model:Qwen/Qwen2.5-Omni-7B",
"base_model:quantized:Qwen/Qwen2.5-Omni-7B",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 22,
"downloads": 633,
"gated": false,
"private": false,
"last_modified": "2025-05-26T09:30:23.000Z",
"created_at": "2025-05-26T09:20:45.000Z",
"pipeline_tag": "any-to-any",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6834326dbce23898b210ff2b",
"id": "ggml-org/Qwen2.5-Omni-7B-GGUF",
"modelId": "ggml-org/Qwen2.5-Omni-7B-GGUF",
"sha": "89b785438c8901d4635e42f50480ba5985a1bbf1",
"createdAt": "2025-05-26T09:20:45.000Z",
"lastModified": "2025-05-26T09:30:23.000Z",
"author": "ggml-org",
"downloads": 633,
"likes": 22,
"gated": false,
"private": false,
"pipeline_tag": "any-to-any",
"library_name": "",
"siblings_count": 7
}