richarderkhov/defetya_-_qwen-1.8b-saiga-gguf overview
Quantization made by Richard Erkhov. Github Discord Request more models qwen-1.8B-saiga - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | qwen-1.8B-saiga.Q2K.gguf | Q2K | 0.79GB | | qwen-1.8B-saiga.Q3KS.gguf | Q3KS | 0.89GB | | qwen-1.8B-saiga.Q3K.gguf | Q3K | 0.95GB | | qwen-1.8B-saiga.Q3KM.gguf | Q3KM | 0.95GB | | qwen-1.8B-saiga.Q3KL.gguf | Q3KL | 0.98GB | | qwen-1.8B-saiga.IQ4XS.gguf | IQ4XS | 1.01GB | | qwen-1.8B-saiga.Q40.gguf | Q40 | 1.04GB | | qwen-1.8B-saiga.IQ4NL.gguf | IQ4NL | 1.05GB | | qwen-1.8B-saiga.Q4KS.gguf | Q4KS | 1.08GB | | qwen-1.8B-saiga.Q4K.gguf | Q4K | 1.13GB | | qwen-1.8B-saiga.Q4KM.gguf | Q4KM | 1.13GB | | qwen-1.8B-saiga.Q41.gguf | Q41 | 1.13GB | | qwen-1.8B-saiga.Q50.gguf | Q50 | 1.22GB | | qwen-1.8B-saiga.Q5KS.gguf | Q5KS | 1.24GB | | qwen-1.8B-saiga.Q5K.gguf | Q5K | 1.28GB | | qwen-1.8B-saiga.Q5KM.gguf | Q5KM | 1.28GB | | qwen-1.8B-saiga.Q51.gguf | Q51 | 1.31GB | | qwen-1.8B-saiga.Q6K.gguf | Q6K | 1.47GB | | qwen-1.8B-saiga.Q80.gguf | Q80 | 1.82GB | Original model description: --- license: apache-2.0 ---
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| qwen-1.8B-saiga.IQ4_NL.gguf | GGUF | IQ4_NL | 1.05 GB | Download |
| qwen-1.8B-saiga.IQ4_XS.gguf | GGUF | IQ4_XS | 1.01 GB | Download |
| qwen-1.8B-saiga.Q2_K.gguf | GGUF | Q2_K | 807.35 MB | Download |
| qwen-1.8B-saiga.Q3_K.gguf | GGUF | Q3_K | 968.82 MB | Download |
| qwen-1.8B-saiga.Q3_K_L.gguf | GGUF | Q3_K_L | 1007.27 MB | Download |
| qwen-1.8B-saiga.Q3_K_M.gguf | GGUF | Q3_K_M | 968.82 MB | Download |
| qwen-1.8B-saiga.Q3_K_S.gguf | GGUF | Q3_K_S | 909.40 MB | Download |
| qwen-1.8B-saiga.Q4_0.gguf | GGUF | — | 1.04 GB | Download |
| qwen-1.8B-saiga.Q4_1.gguf | GGUF | — | 1.13 GB | Download |
| qwen-1.8B-saiga.Q4_K.gguf | GGUF | Q4_K | 1.13 GB | Download |
| qwen-1.8B-saiga.Q4_K_M.gguf | GGUF | Q4_K_M | 1.13 GB | Download |
| qwen-1.8B-saiga.Q4_K_S.gguf | GGUF | Q4_K_S | 1.08 GB | Download |
| qwen-1.8B-saiga.Q5_0.gguf | GGUF | — | 1.22 GB | Download |
| qwen-1.8B-saiga.Q5_1.gguf | GGUF | — | 1.31 GB | Download |
| qwen-1.8B-saiga.Q5_K.gguf | GGUF | Q5_K | 1.28 GB | Download |
| qwen-1.8B-saiga.Q5_K_M.gguf | GGUF | Q5_K_M | 1.28 GB | Download |
| qwen-1.8B-saiga.Q5_K_S.gguf | GGUF | Q5_K_S | 1.24 GB | Download |
| qwen-1.8B-saiga.Q6_K.gguf | GGUF | Q6_K | 1.47 GB | Download |
| qwen-1.8B-saiga.Q8_0.gguf | GGUF | — | 1.82 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "",
"summary": "Quantization made by Richard Erkhov. Github Discord Request more models qwen-1.8B-saiga - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | qwen-1.8B-saiga.Q2_K.gguf | Q2_K | 0.79GB | | qwen-1.8B-saiga.Q3_K_S.gguf | Q3_K_S | 0.89GB | | qwen-1.8B-saiga.Q3_K.gguf | Q3_K | 0.95GB | | qwen-1.8B-saiga.Q3_K_M.gguf | Q3_K_M | 0.95GB | | qwen-1.8B-saiga.Q3_K_L.gguf | Q3_K_L | 0.98GB | | qwen-1.8B-saiga.IQ4_XS.gguf | IQ4_XS | 1.01GB | | qwen-1.8B-saiga.Q4_0.gguf | Q4_0 | 1.04GB | | qwen-1.8B-saiga.IQ4_NL.gguf | IQ4_NL | 1.05GB | | qwen-1.8B-saiga.Q4_K_S.gguf | Q4_K_S | 1.08GB | | qwen-1.8B-saiga.Q4_K.gguf | Q4_K | 1.13GB | | qwen-1.8B-saiga.Q4_K_M.gguf | Q4_K_M | 1.13GB | | qwen-1.8B-saiga.Q4_1.gguf | Q4_1 | 1.13GB | | qwen-1.8B-saiga.Q5_0.gguf | Q5_0 | 1.22GB | | qwen-1.8B-saiga.Q5_K_S.gguf | Q5_K_S | 1.24GB | | qwen-1.8B-saiga.Q5_K.gguf | Q5_K | 1.28GB | | qwen-1.8B-saiga.Q5_K_M.gguf | Q5_K_M | 1.28GB | | qwen-1.8B-saiga.Q5_1.gguf | Q5_1 | 1.31GB | | qwen-1.8B-saiga.Q6_K.gguf | Q6_K | 1.47GB | | qwen-1.8B-saiga.Q8_0.gguf | Q8_0 | 1.82GB | Original model description: --- license: apache-2.0 ---",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nqwen-1.8B-saiga - GGUF\n- Model creator: https://huggingface.co/Defetya/\n- Original model: https://huggingface.co/Defetya/qwen-1.8B-saiga/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [qwen-1.8B-saiga.Q2_K.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q2_K.gguf) | Q2_K | 0.79GB |\n| [qwen-1.8B-saiga.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q3_K_S.gguf) | Q3_K_S | 0.89GB |\n| [qwen-1.8B-saiga.Q3_K.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q3_K.gguf) | Q3_K | 0.95GB |\n| [qwen-1.8B-saiga.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q3_K_M.gguf) | Q3_K_M | 0.95GB |\n| [qwen-1.8B-saiga.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q3_K_L.gguf) | Q3_K_L | 0.98GB |\n| [qwen-1.8B-saiga.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.IQ4_XS.gguf) | IQ4_XS | 1.01GB |\n| [qwen-1.8B-saiga.Q4_0.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q4_0.gguf) | Q4_0 | 1.04GB |\n| [qwen-1.8B-saiga.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.IQ4_NL.gguf) | IQ4_NL | 1.05GB |\n| [qwen-1.8B-saiga.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q4_K_S.gguf) | Q4_K_S | 1.08GB |\n| [qwen-1.8B-saiga.Q4_K.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q4_K.gguf) | Q4_K | 1.13GB |\n| [qwen-1.8B-saiga.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q4_K_M.gguf) | Q4_K_M | 1.13GB |\n| [qwen-1.8B-saiga.Q4_1.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q4_1.gguf) | Q4_1 | 1.13GB |\n| [qwen-1.8B-saiga.Q5_0.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q5_0.gguf) | Q5_0 | 1.22GB |\n| [qwen-1.8B-saiga.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q5_K_S.gguf) | Q5_K_S | 1.24GB |\n| [qwen-1.8B-saiga.Q5_K.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q5_K.gguf) | Q5_K | 1.28GB |\n| [qwen-1.8B-saiga.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q5_K_M.gguf) | Q5_K_M | 1.28GB |\n| [qwen-1.8B-saiga.Q5_1.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q5_1.gguf) | Q5_1 | 1.31GB |\n| [qwen-1.8B-saiga.Q6_K.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q6_K.gguf) | Q6_K | 1.47GB |\n| [qwen-1.8B-saiga.Q8_0.gguf](https://huggingface.co/RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf/blob/main/qwen-1.8B-saiga.Q8_0.gguf) | Q8_0 | 1.82GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\n---\n\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 1206,
"gated": false,
"private": false,
"last_modified": "2024-11-01T17:08:48.000Z",
"created_at": "2024-11-01T16:43:40.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6725053c0374f5ebed3b37d1",
"id": "RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf",
"modelId": "RichardErkhov/Defetya_-_qwen-1.8B-saiga-gguf",
"sha": "f538a3c4a926735d1240e4a4491b6d351e39c782",
"createdAt": "2024-11-01T16:43:40.000Z",
"lastModified": "2024-11-01T17:08:48.000Z",
"author": "RichardErkhov",
"downloads": 1206,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 21
}