alcoft/qwen_qwen3-1.7b-gguf 1.7B_Q8_0 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
alcoft/qwen_qwen3-1.7b-gguf overview
|Quant|Size|Description| |---|---|---| |Q2K|839.13 MB|Not recommended for most people. Very low quality.| |Q2KL|1.1 GB|Not recommended for most people. Uses Q80 for output and embedding, and Q2K for everything else. Very low quality.| |Q2KXL|1.65 GB|Not recommended for most people. Uses F16 for output and embedding, and Q2K for everything else. Very low quality.| |Q3KS|954.59 MB|Not recommended for most people. Prefer any bigger Q3K quantization. Low quality.| |Q3KM|1023.52 MB|Not recommended for most people. Low quality.| |Q3KL|1.06 GB|Not recommended for most people. Low quality.| |Q3KXL|1.31 GB|Not recommended for most people. Uses Q80 for output and embedding, and Q3KL for everything else. Low quality.| |Q3KXXL|1.86 GB|Not recommended for most people. Uses F16 for output and embedding, and Q3KL for everything else. Low quality.| |Q4KS|1.15 GB|Recommended. Slightly low quality.| |Q4KM|1.19 GB|Recommended. Decent quality for most use cases.| |Q4KL|1.41 GB|Recommended. Uses Q80 for output and embedding, and Q4KM for everything else. Decent quality.| |Q4KXL|1.95 GB|Recommended. Uses F16 for output and embedding, and Q4KM for everything else. Decent quality.| |Q5KS|1.35 GB|Recommended. High quality.| |Q5KM|1.37 GB|Recommended. High quality.| |Q5KL|1.55 GB|Recommended. Uses Q80 for output and embedding, and Q5KM for everything else. High quality.| |Q5KXL|2.09 GB|Recommended. Uses F16 for output and embedding, and Q5KM for everything else. High quality.| |Q6K|1.56 GB|Recommended. Very high quality.| |Q6KL|1.7 GB|Recommended. Uses Q80 for output and embedding, and Q6K for everything else. Very high quality.| |Q6KXL|2.24 GB|Recommended. Uses F16 for output and embedding, and Q6K for everything else. Very high quality.| |Q80|2.02 GB|Recommended. Quality almost like F16.| |Q8KXL|2.56 GB|Recommended. Uses F16 for output and embedding, and Q80 for everything else. Quality almost like F16.| |F16|3.79 GB|Not recommended. Overkill. Prefer Q80.| |ORIGINAL (BF16)|3.79 GB|Not recommended. Overkill. Prefer Q80.| --- Quantized using TAO71-AI AutoQuantizer. You can check out the original model card here.
Downloads
662
Likes
0
Pipeline
text-generation
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
23 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen_Qwen3-1.7B.gguf | GGUF | — | 3.79 GB | Download |
| Qwen_Qwen3-1.7B_F16.gguf | GGUF | F16 | 3.79 GB | Download |
| Qwen_Qwen3-1.7B_Q2_K.gguf | GGUF | Q2_K | 839.13 MB | Download |
| Qwen_Qwen3-1.7B_Q2_K_L.gguf | GGUF | Q2_K_L | 1.10 GB | Download |
| Qwen_Qwen3-1.7B_Q2_K_XL.gguf | GGUF | Q2_K_XL | 1.65 GB | Download |
| Qwen_Qwen3-1.7B_Q3_K_L.gguf | GGUF | Q3_K_L | 1.06 GB | Download |
| Qwen_Qwen3-1.7B_Q3_K_M.gguf | GGUF | Q3_K_M | 1023.52 MB | Download |
| Qwen_Qwen3-1.7B_Q3_K_S.gguf | GGUF | Q3_K_S | 954.59 MB | Download |
| Qwen_Qwen3-1.7B_Q3_K_XL.gguf | GGUF | Q3_K_XL | 1.31 GB | Download |
| Qwen_Qwen3-1.7B_Q3_K_XXL.gguf | GGUF | Q3_K_XXL | 1.86 GB | Download |
| Qwen_Qwen3-1.7B_Q4_K_L.gguf | GGUF | Q4_K_L | 1.41 GB | Download |
| Qwen_Qwen3-1.7B_Q4_K_M.gguf | GGUF | Q4_K_M | 1.19 GB | Download |
| Qwen_Qwen3-1.7B_Q4_K_S.gguf | GGUF | Q4_K_S | 1.15 GB | Download |
| Qwen_Qwen3-1.7B_Q4_K_XL.gguf | GGUF | Q4_K_XL | 1.95 GB | Download |
| Qwen_Qwen3-1.7B_Q5_K_L.gguf | GGUF | Q5_K_L | 1.55 GB | Download |
| Qwen_Qwen3-1.7B_Q5_K_M.gguf | GGUF | Q5_K_M | 1.37 GB | Download |
| Qwen_Qwen3-1.7B_Q5_K_S.gguf | GGUF | Q5_K_S | 1.35 GB | Download |
| Qwen_Qwen3-1.7B_Q5_K_XL.gguf | GGUF | Q5_K_XL | 2.09 GB | Download |
| Qwen_Qwen3-1.7B_Q6_K.gguf | GGUF | Q6_K | 1.56 GB | Download |
| Qwen_Qwen3-1.7B_Q6_K_L.gguf | GGUF | Q6_K_L | 1.70 GB | Download |
| Qwen_Qwen3-1.7B_Q6_K_XL.gguf | GGUF | Q6_K_XL | 2.24 GB | Download |
| Qwen_Qwen3-1.7B_Q8_0.gguf | GGUF | — | 2.02 GB | Download |
| Qwen_Qwen3-1.7B_Q8_K_XL.gguf | GGUF | Q8_K_XL | 2.56 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": [
"Qwen/Qwen3-1.7B"
],
"pipeline_tag": "text-generation",
"frontmatter": {
"base_model": [
"Qwen/Qwen3-1.7B"
],
"pipeline_tag": "text-generation"
},
"hero_image_url": "",
"summary": "|Quant|Size|Description| |---|---|---| |Q2_K|839.13 MB|Not recommended for most people. Very low quality.| |Q2_K_L|1.1 GB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q2_K for everything else. Very low quality.| |Q2_K_XL|1.65 GB|Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.| |Q3_K_S|954.59 MB|Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.| |Q3_K_M|1023.52 MB|Not recommended for most people. Low quality.| |Q3_K_L|1.06 GB|Not recommended for most people. Low quality.| |Q3_K_XL|1.31 GB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q3_K_L for everything else. Low quality.| |Q3_K_XXL|1.86 GB|Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality.| |Q4_K_S|1.15 GB|Recommended. Slightly low quality.| |Q4_K_M|1.19 GB|Recommended. Decent quality for most use cases.| |Q4_K_L|1.41 GB|Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality.| |Q4_K_XL|1.95 GB|Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.| |Q5_K_S|1.35 GB|Recommended. High quality.| |Q5_K_M|1.37 GB|Recommended. High quality.| |Q5_K_L|1.55 GB|Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality.| |Q5_K_XL|2.09 GB|Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.| |Q6_K|1.56 GB|Recommended. Very high quality.| |Q6_K_L|1.7 GB|Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality.| |Q6_K_XL|2.24 GB|Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.| |Q8_0|2.02 GB|Recommended. Quality almost like F16.| |Q8_K_XL|2.56 GB|Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.| |F16|3.79 GB|Not recommended. Overkill. Prefer Q8_0.| |ORIGINAL (BF16)|3.79 GB|Not recommended. Overkill. Prefer Q8_0.| --- Quantized using TAO71-AI AutoQuantizer. You can check out the original model card here.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model:\n- Qwen/Qwen3-1.7B\npipeline_tag: text-generation\n---\n\n|Quant|Size|Description|\n|---|---|---|\n|[Q2_K](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q2_K.gguf)|839.13 MB|Not recommended for most people. Very low quality.|\n|[Q2_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q2_K_L.gguf)|1.1 GB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q2_K for everything else. Very low quality.|\n|[Q2_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q2_K_XL.gguf)|1.65 GB|Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.|\n|[Q3_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q3_K_S.gguf)|954.59 MB|Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.|\n|[Q3_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q3_K_M.gguf)|1023.52 MB|Not recommended for most people. Low quality.|\n|[Q3_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q3_K_L.gguf)|1.06 GB|Not recommended for most people. Low quality.|\n|[Q3_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q3_K_XL.gguf)|1.31 GB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q3_K_L for everything else. Low quality.|\n|[Q3_K_XXL](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q3_K_XXL.gguf)|1.86 GB|Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality.|\n|[Q4_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q4_K_S.gguf)|1.15 GB|Recommended. Slightly low quality.|\n|[Q4_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q4_K_M.gguf)|1.19 GB|Recommended. Decent quality for most use cases.|\n|[Q4_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q4_K_L.gguf)|1.41 GB|Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality.|\n|[Q4_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q4_K_XL.gguf)|1.95 GB|Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.|\n|[Q5_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q5_K_S.gguf)|1.35 GB|Recommended. High quality.|\n|[Q5_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q5_K_M.gguf)|1.37 GB|Recommended. High quality.|\n|[Q5_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q5_K_L.gguf)|1.55 GB|Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality.|\n|[Q5_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q5_K_XL.gguf)|2.09 GB|Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.|\n|[Q6_K](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q6_K.gguf)|1.56 GB|Recommended. Very high quality.|\n|[Q6_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q6_K_L.gguf)|1.7 GB|Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality.|\n|[Q6_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q6_K_XL.gguf)|2.24 GB|Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.|\n|[Q8_0](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q8_0.gguf)|2.02 GB|Recommended. Quality almost like F16.|\n|[Q8_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_Q8_K_XL.gguf)|2.56 GB|Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.|\n|[F16](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B_F16.gguf)|3.79 GB|Not recommended. Overkill. Prefer Q8_0.|\n|[ORIGINAL (BF16)](https://huggingface.co/Alcoft/Qwen_Qwen3-1.7B-GGUF/resolve/main/Qwen_Qwen3-1.7B.gguf)|3.79 GB|Not recommended. Overkill. Prefer Q8_0.|\n\n---\n\nQuantized using [TAO71-AI AutoQuantizer](https://github.com/TAO71-AI/AutoQuantizer).\nYou can check out the original model card [here](https://huggingface.co/Qwen/Qwen3-1.7B).",
"related_quantizations": []
},
"tags": [
"gguf",
"text-generation",
"base_model:Qwen/Qwen3-1.7B",
"base_model:quantized:Qwen/Qwen3-1.7B",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 662,
"gated": false,
"private": false,
"last_modified": "2025-08-11T01:22:27.000Z",
"created_at": "2025-08-11T01:10:31.000Z",
"pipeline_tag": "text-generation",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "689943071112b44fe240def4",
"id": "Alcoft/Qwen_Qwen3-1.7B-GGUF",
"modelId": "Alcoft/Qwen_Qwen3-1.7B-GGUF",
"sha": "b559163690d71198cdc4606b8bca43721500e1c8",
"createdAt": "2025-08-11T01:10:31.000Z",
"lastModified": "2025-08-11T01:22:27.000Z",
"author": "Alcoft",
"downloads": 662,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "",
"siblings_count": 25
}