Model Intelligence Sheet
richarderkhov/famepram_-_qwen2.5-1b-gguf overview
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Downloads
176
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 |
|---|---|---|---|---|
| qwen2.5-1b.IQ3_M.gguf | GGUF | IQ3_M | 740.68 MB | Download |
| qwen2.5-1b.IQ3_S.gguf | GGUF | IQ3_S | 727.09 MB | Download |
| qwen2.5-1b.IQ3_XS.gguf | GGUF | IQ3_XS | 697.80 MB | Download |
| qwen2.5-1b.IQ4_NL.gguf | GGUF | IQ4_NL | 897.87 MB | Download |
| qwen2.5-1b.IQ4_XS.gguf | GGUF | IQ4_XS | 860.39 MB | Download |
| qwen2.5-1b.Q2_K.gguf | GGUF | Q2_K | 644.97 MB | Download |
| qwen2.5-1b.Q3_K.gguf | GGUF | Q3_K | 786.00 MB | Download |
| qwen2.5-1b.Q3_K_L.gguf | GGUF | Q3_K_L | 839.39 MB | Download |
| qwen2.5-1b.Q3_K_M.gguf | GGUF | Q3_K_M | 786.00 MB | Download |
| qwen2.5-1b.Q3_K_S.gguf | GGUF | Q3_K_S | 725.69 MB | Download |
| qwen2.5-1b.Q4_0.gguf | GGUF | — | 891.64 MB | Download |
| qwen2.5-1b.Q4_1.gguf | GGUF | — | 969.73 MB | Download |
| qwen2.5-1b.Q4_K.gguf | GGUF | Q4_K | 940.37 MB | Download |
| qwen2.5-1b.Q4_K_M.gguf | GGUF | Q4_K_M | 940.37 MB | Download |
| qwen2.5-1b.Q4_K_S.gguf | GGUF | Q4_K_S | 896.75 MB | Download |
| qwen2.5-1b.Q5_0.gguf | GGUF | — | 1.02 GB | Download |
| qwen2.5-1b.Q5_1.gguf | GGUF | — | 1.10 GB | Download |
| qwen2.5-1b.Q5_K.gguf | GGUF | Q5_K | 1.05 GB | Download |
| qwen2.5-1b.Q5_K_M.gguf | GGUF | Q5_K_M | 1.05 GB | Download |
| qwen2.5-1b.Q5_K_S.gguf | GGUF | Q5_K_S | 1.02 GB | Download |
| qwen2.5-1b.Q6_K.gguf | GGUF | Q6_K | 1.19 GB | Download |
| qwen2.5-1b.Q8_0.gguf | GGUF | — | 1.53 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png",
"summary": "This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.",
"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\nqwen2.5-1b - GGUF\n- Model creator: https://huggingface.co/famepram/\n- Original model: https://huggingface.co/famepram/qwen2.5-1b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [qwen2.5-1b.Q2_K.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q2_K.gguf) | Q2_K | 0.63GB |\n| [qwen2.5-1b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.IQ3_XS.gguf) | IQ3_XS | 0.68GB |\n| [qwen2.5-1b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.IQ3_S.gguf) | IQ3_S | 0.71GB |\n| [qwen2.5-1b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q3_K_S.gguf) | Q3_K_S | 0.71GB |\n| [qwen2.5-1b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.IQ3_M.gguf) | IQ3_M | 0.72GB |\n| [qwen2.5-1b.Q3_K.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q3_K.gguf) | Q3_K | 0.77GB |\n| [qwen2.5-1b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q3_K_M.gguf) | Q3_K_M | 0.77GB |\n| [qwen2.5-1b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q3_K_L.gguf) | Q3_K_L | 0.82GB |\n| [qwen2.5-1b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.IQ4_XS.gguf) | IQ4_XS | 0.84GB |\n| [qwen2.5-1b.Q4_0.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q4_0.gguf) | Q4_0 | 0.87GB |\n| [qwen2.5-1b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.IQ4_NL.gguf) | IQ4_NL | 0.88GB |\n| [qwen2.5-1b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q4_K_S.gguf) | Q4_K_S | 0.88GB |\n| [qwen2.5-1b.Q4_K.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q4_K.gguf) | Q4_K | 0.92GB |\n| [qwen2.5-1b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q4_K_M.gguf) | Q4_K_M | 0.92GB |\n| [qwen2.5-1b.Q4_1.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q4_1.gguf) | Q4_1 | 0.95GB |\n| [qwen2.5-1b.Q5_0.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q5_0.gguf) | Q5_0 | 1.02GB |\n| [qwen2.5-1b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q5_K_S.gguf) | Q5_K_S | 1.02GB |\n| [qwen2.5-1b.Q5_K.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q5_K.gguf) | Q5_K | 1.05GB |\n| [qwen2.5-1b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q5_K_M.gguf) | Q5_K_M | 1.05GB |\n| [qwen2.5-1b.Q5_1.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q5_1.gguf) | Q5_1 | 1.1GB |\n| [qwen2.5-1b.Q6_K.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q6_K.gguf) | Q6_K | 1.19GB |\n| [qwen2.5-1b.Q8_0.gguf](https://huggingface.co/RichardErkhov/famepram_-_qwen2.5-1b-gguf/blob/main/qwen2.5-1b.Q8_0.gguf) | Q8_0 | 1.53GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: unsloth/qwen2.5-1.5b-bnb-4bit\ntags:\n- text-generation-inference\n- transformers\n- unsloth\n- qwen2\n- trl\n- sft\nlicense: apache-2.0\nlanguage:\n- en\n---\n\n# Uploaded model\n\n- **Developed by:** famepram\n- **License:** apache-2.0\n- **Finetuned from model :** unsloth/qwen2.5-1.5b-bnb-4bit\n\nThis qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.\n\n[<img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png\" width=\"200\"/>](https://github.com/unslothai/unsloth)\n\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us"
],
"likes": 0,
"downloads": 176,
"gated": false,
"private": false,
"last_modified": "2025-02-19T22:24:46.000Z",
"created_at": "2025-02-19T21:41:41.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "67b65015848b843f0c17415e",
"id": "RichardErkhov/famepram_-_qwen2.5-1b-gguf",
"modelId": "RichardErkhov/famepram_-_qwen2.5-1b-gguf",
"sha": "9b2246bf409d89a9b82451b965799379860e4c3b",
"createdAt": "2025-02-19T21:41:41.000Z",
"lastModified": "2025-02-19T22:24:46.000Z",
"author": "RichardErkhov",
"downloads": 176,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}