Model Intelligence Sheet
rodrigomt/qwen3-30b-a3b-thinking-deepseek-distill-2507-v3.1-v2-gguf overview
Quantized version of: BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2-FP32 ---
Downloads
194
Likes
6
Pipeline
text-generation
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
6 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-F16-00001-of-00003.gguf | GGUF | F16 | 27.67 GB | Download |
| Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-F16-00002-of-00003.gguf | GGUF | F16 | 27.53 GB | Download |
| Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-F16-00003-of-00003.gguf | GGUF | F16 | 1.71 GB | Download |
| Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-UD-Q3_K_XL.gguf | GGUF | Q3_K_XL | 12.88 GB | Download |
| Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-UD-Q4_K_XL.gguf | GGUF | Q4_K_XL | 16.50 GB | Download |
| Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-UD-Q5_K_XL.gguf | GGUF | Q5_K_XL | 20.27 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": [
"BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2-FP32"
],
"pipeline_tag": "text-generation",
"frontmatter": {
"base_model": [
"BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2-FP32"
],
"pipeline_tag": "text-generation"
},
"hero_image_url": "",
"summary": "Quantized version of: BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2-FP32 ---",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model:\n- BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2-FP32\npipeline_tag: text-generation\n---\n\n# 🧠 Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2 GGUFs\n\nQuantized version of: [BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2-FP32](https://huggingface.co/BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-V2-FP32)\n\n---\n\n## 📦 Available GGUFs\n\n| Format | Description |\n|--------|-------------|\n| **F16** | Full precision (16-bit), better quality, larger size ⚖️ |\n| **Q5_K_XL** | Quantized (5-bit XL variant, based on the quantization table of the unsloth model Qwen3-30B-A3B-Thinking-2507), medium size, faster inference ⚡ |\n| **Q4_K_XL** | Quantized (4-bit XL variant, based on the quantization table of the unsloth model Qwen3-30B-A3B-Thinking-2507), smaller size, faster inference ⚡ |\n| **Q3_K_XL** | Quantized (3-bit XL variant, based on the quantization table of the unsloth model Qwen3-30B-A3B-Thinking-2507), smaller size, faster inference ⚡ |\n\n---\n\n## 🚀 Usage\n\nExample with `llama.cpp`:\n\n```bash\n./main -m ./gguf-file-name.gguf -p \"Hello world!\"\n````",
"related_quantizations": []
},
"tags": [
"gguf",
"text-generation",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 6,
"downloads": 194,
"gated": false,
"private": false,
"last_modified": "2025-10-06T01:40:36.000Z",
"created_at": "2025-09-18T22:06:23.000Z",
"pipeline_tag": "text-generation",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "68cc825f758e72528ed5a6c0",
"id": "rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF",
"modelId": "rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF",
"sha": "7169db0294c901802ce1e547f5d9583c40c6249f",
"createdAt": "2025-09-18T22:06:23.000Z",
"lastModified": "2025-10-06T01:40:36.000Z",
"author": "rodrigomt",
"downloads": 194,
"likes": 6,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "",
"siblings_count": 8
}