ermiaazarkhalili/qwen3.5-0.8b-sft-claude-reasoning-unsloth-gguf Q5_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
ermiaazarkhalili/qwen3.5-0.8b-sft-claude-reasoning-unsloth-gguf overview
GGUF quantized versions of Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth for llama.cpp, Ollama, LM Studio.
Downloads
310
Likes
0
Pipeline
text-generation
Library
gguf
Visibility
Public
Access
Open
Repository Files & Downloads
6 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q2_K.gguf | GGUF | Q2_K | 402.76 MB | Download |
| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q3_K_M.gguf | GGUF | Q3_K_M | 444.62 MB | Download |
| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q4_K_M.gguf | GGUF | Q4_K_M | 504.78 MB | Download |
| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q5_K_M.gguf | GGUF | Q5_K_M | 551.22 MB | Download |
| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q6_K.gguf | GGUF | Q6_K | 600.57 MB | Download |
| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q8_0.gguf | GGUF | — | 774.23 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "apache-2.0",
"language": [
"en"
],
"library_name": "gguf",
"pipeline_tag": "text-generation",
"tags": [
"gguf",
"quantized",
"llama-cpp",
"ollama",
"unsloth",
"sft",
"reasoning"
],
"base_model": "ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth",
"frontmatter": {
"license": "apache-2.0",
"language": [
"en"
],
"library_name": "gguf",
"pipeline_tag": "text-generation",
"tags": [
"gguf",
"quantized",
"llama-cpp",
"ollama",
"unsloth",
"sft",
"reasoning"
],
"base_model": "ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth"
},
"hero_image_url": "",
"summary": "GGUF quantized versions of Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth for llama.cpp, Ollama, LM Studio.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n - en\nlibrary_name: gguf\npipeline_tag: text-generation\ntags:\n - gguf\n - quantized\n - llama-cpp\n - ollama\n - unsloth\n - sft\n - reasoning\nbase_model: ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth\n---\n\n# Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth — GGUF\n\nGGUF quantized versions of [Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth](https://huggingface.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth) for llama.cpp, Ollama, LM Studio.\n\n## Available Quantizations\n\n| File | Quant | Size | Use Case |\n|------|-------|------|----------|\n| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q2_K.gguf | Q2_K | ~small | Edge/mobile |\n| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q3_K_M.gguf | Q3_K_M | ~small | Constrained |\n| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q4_K_M.gguf | Q4_K_M | ~medium | **Recommended** |\n| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q5_K_M.gguf | Q5_K_M | ~medium | Higher quality |\n| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q6_K.gguf | Q6_K | ~large | Near-lossless |\n| Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-Q8_0.gguf | Q8_0 | ~large | Maximum quality |\n\n## Ollama\n\n```bash\nollama pull hf.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUF:Q4_K_M\nollama run hf.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUF:Q4_K_M \"Hello!\"\n```\n\n## Source\n\n- **Model**: [Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth](https://huggingface.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth)\n- **Base**: [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B)\n- **Task**: SFT Distillation\n- **Framework**: Unsloth (2x faster training)\n\n## Citation\n\n```bibtex\n@misc{azarkhalili2026qwen35_08b_sft_claude_reasoning_unsloth,\n author = {Azarkhalili, Behrooz},\n title = {Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUF},\n year = {2026},\n publisher = {Hugging Face},\n url = {https://huggingface.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUF}\n}\n```\n",
"related_quantizations": []
},
"tags": [
"gguf",
"quantized",
"llama-cpp",
"ollama",
"unsloth",
"sft",
"reasoning",
"text-generation",
"en",
"base_model:ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth",
"base_model:quantized:ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 310,
"gated": false,
"private": false,
"last_modified": "2026-04-15T17:11:56.000Z",
"created_at": "2026-04-15T17:07:48.000Z",
"pipeline_tag": "text-generation",
"library_name": "gguf"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69dfc5e45cde98a92f0c68bb",
"id": "ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUF",
"modelId": "ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUF",
"sha": "bb4a28a372e1c5b8bfd8c241a4f42f69d6f34d53",
"createdAt": "2026-04-15T17:07:48.000Z",
"lastModified": "2026-04-15T17:11:56.000Z",
"author": "ermiaazarkhalili",
"downloads": 310,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "gguf",
"siblings_count": 8
}