Model Intelligence Sheet
teichai/qwen3-8b-deepseek-v3.2-speciale-distill-gguf overview
This model was finetuned and converted to GGUF format using Unsloth. Example usage:
Downloads
12,690
Likes
23
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
13 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.bf16.gguf | GGUF | BF16 | 15.26 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_m.gguf | GGUF | IQ2_M | 2.84 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_xs.gguf | GGUF | IQ2_XS | 2.51 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_m.gguf | GGUF | IQ3_M | 3.63 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_xs.gguf | GGUF | IQ3_XS | 3.38 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_nl.gguf | GGUF | IQ4_NL | 4.49 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_xs.gguf | GGUF | IQ4_XS | 4.25 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_m.gguf | GGUF | Q3_K_M | 3.84 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_s.gguf | GGUF | Q3_K_S | 3.51 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q4_k_m.gguf | GGUF | Q4_K_M | 4.68 GB | Download |
| Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q8_0.gguf | GGUF | — | 8.11 GB | Download |
| qwen3-8b.F16.gguf | GGUF | F16 | 15.26 GB | Download |
| qwen3-8b.Q8_0.gguf | GGUF | — | 8.11 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"tags": [
"gguf",
"llama.cpp",
"unsloth"
],
"datasets": [
"TeichAI/deepseek-v3.2-speciale-1000x"
],
"base_model": [
"TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill"
],
"frontmatter": {
"tags": [
"gguf",
"llama.cpp",
"unsloth"
],
"datasets": [
"TeichAI/deepseek-v3.2-speciale-1000x"
],
"base_model": [
"TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill"
]
},
"hero_image_url": "",
"summary": "This model was finetuned and converted to GGUF format using Unsloth. **Example usage**:",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\ntags:\n- gguf\n- llama.cpp\n- unsloth\ndatasets:\n- TeichAI/deepseek-v3.2-speciale-1000x\nbase_model:\n- TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill\n---\n\n# Qwen3-8B-DeepSeek-v3.2-Speciale-Distill-GGUF - GGUF\n\nThis model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).\n\n**Example usage**:\n- For text only LLMs: **llama-cli** **--hf** repo_id/model_name **-p** \"why is the sky blue?\"\n- For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf\n\n## Available Model files:\n- `qwen3-8b.Q8_0.gguf`\n- `qwen3-8b.F16.gguf`\n\n## Ollama\nAn Ollama Modelfile is included for easy deployment.",
"related_quantizations": []
},
"tags": [
"gguf",
"qwen3",
"llama.cpp",
"unsloth",
"dataset:TeichAI/deepseek-v3.2-speciale-1000x",
"base_model:TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill",
"base_model:quantized:TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 23,
"downloads": 12690,
"gated": false,
"private": false,
"last_modified": "2025-12-10T06:24:34.000Z",
"created_at": "2025-12-05T02:27:18.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6932430687e8d4eafe40a45a",
"id": "TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill-GGUF",
"modelId": "TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill-GGUF",
"sha": "789b30f3ff7fe9101a99d02eefe8728fdfb4792d",
"createdAt": "2025-12-05T02:27:18.000Z",
"lastModified": "2025-12-10T06:24:34.000Z",
"author": "TeichAI",
"downloads": 12690,
"likes": 23,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 17
}