Model Intelligence Sheet
richarderkhov/bondds_-_04-6905grapph-gguf overview
This is a merge of pre-trained language models created using mergekit.
Downloads
87
Likes
0
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
22 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| 04-6905grapph.IQ3_M.gguf | GGUF | IQ3_M | 3.52 GB | Download |
| 04-6905grapph.IQ3_S.gguf | GGUF | IQ3_S | 3.43 GB | Download |
| 04-6905grapph.IQ3_XS.gguf | GGUF | IQ3_XS | 3.28 GB | Download |
| 04-6905grapph.IQ4_NL.gguf | GGUF | IQ4_NL | 4.38 GB | Download |
| 04-6905grapph.IQ4_XS.gguf | GGUF | IQ4_XS | 4.18 GB | Download |
| 04-6905grapph.Q2_K.gguf | GGUF | Q2_K | 2.96 GB | Download |
| 04-6905grapph.Q3_K.gguf | GGUF | Q3_K | 3.74 GB | Download |
| 04-6905grapph.Q3_K_L.gguf | GGUF | Q3_K_L | 4.03 GB | Download |
| 04-6905grapph.Q3_K_M.gguf | GGUF | Q3_K_M | 3.74 GB | Download |
| 04-6905grapph.Q3_K_S.gguf | GGUF | Q3_K_S | 3.41 GB | Download |
| 04-6905grapph.Q4_0.gguf | GGUF | — | 4.34 GB | Download |
| 04-6905grapph.Q4_1.gguf | GGUF | — | 4.78 GB | Download |
| 04-6905grapph.Q4_K.gguf | GGUF | Q4_K | 4.58 GB | Download |
| 04-6905grapph.Q4_K_M.gguf | GGUF | Q4_K_M | 4.58 GB | Download |
| 04-6905grapph.Q4_K_S.gguf | GGUF | Q4_K_S | 4.37 GB | Download |
| 04-6905grapph.Q5_0.gguf | GGUF | — | 5.21 GB | Download |
| 04-6905grapph.Q5_1.gguf | GGUF | — | 5.65 GB | Download |
| 04-6905grapph.Q5_K.gguf | GGUF | Q5_K | 5.34 GB | Download |
| 04-6905grapph.Q5_K_M.gguf | GGUF | Q5_K_M | 5.34 GB | Download |
| 04-6905grapph.Q5_K_S.gguf | GGUF | Q5_K_S | 5.21 GB | Download |
| 04-6905grapph.Q6_K.gguf | GGUF | Q6_K | 6.14 GB | Download |
| 04-6905grapph.Q8_0.gguf | GGUF | — | 7.95 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "",
"summary": "This is a merge of pre-trained language models created using mergekit.",
"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\n04-6905grapph - GGUF\n- Model creator: https://huggingface.co/Bondds/\n- Original model: https://huggingface.co/Bondds/04-6905grapph/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [04-6905grapph.Q2_K.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q2_K.gguf) | Q2_K | 2.96GB |\n| [04-6905grapph.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [04-6905grapph.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [04-6905grapph.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [04-6905grapph.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [04-6905grapph.Q3_K.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q3_K.gguf) | Q3_K | 3.74GB |\n| [04-6905grapph.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [04-6905grapph.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [04-6905grapph.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [04-6905grapph.Q4_0.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [04-6905grapph.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [04-6905grapph.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [04-6905grapph.Q4_K.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q4_K.gguf) | Q4_K | 4.58GB |\n| [04-6905grapph.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [04-6905grapph.Q4_1.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [04-6905grapph.Q5_0.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [04-6905grapph.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [04-6905grapph.Q5_K.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q5_K.gguf) | Q5_K | 5.34GB |\n| [04-6905grapph.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [04-6905grapph.Q5_1.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [04-6905grapph.Q6_K.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q6_K.gguf) | Q6_K | 6.14GB |\n| [04-6905grapph.Q8_0.gguf](https://huggingface.co/RichardErkhov/Bondds_-_04-6905grapph-gguf/blob/main/04-6905grapph.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: []\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\n\n---\n# top\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method using /root/top2 as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* /root/top1\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmodels:\n - model: /root/top2\n parameters:\n weight: 0.9468\n - model: /root/top1\n parameters:\n weight: 0.0532\nbase_model: /root/top2\nmerge_method: linear\ndtype: bfloat16\n\n```\n\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"arxiv:2203.05482",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 87,
"gated": false,
"private": false,
"last_modified": "2025-07-10T14:41:00.000Z",
"created_at": "2025-07-10T06:50:20.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "686f62ac6070ec6ad90a5327",
"id": "RichardErkhov/Bondds_-_04-6905grapph-gguf",
"modelId": "RichardErkhov/Bondds_-_04-6905grapph-gguf",
"sha": "1137f3af3d0703b59b89f8a8e4657f6cfbb82fc4",
"createdAt": "2025-07-10T06:50:20.000Z",
"lastModified": "2025-07-10T14:41:00.000Z",
"author": "RichardErkhov",
"downloads": 87,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}