lewdiculous/llama-3-soliloquy-8b-v2-gguf-iq-imatrix IQ3_S 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.
lewdiculous/llama-3-soliloquy-8b-v2-gguf-iq-imatrix overview
Originally these were my personal GGUF-IQ-Imatrix quants of openlynn/Llama-3-Soliloquy-8B-v2. Read the original model page for details. Author: "Soliloquy-L3 is a highly capable roleplaying model designed for immersive, dynamic experiences. Trained on over 250 million tokens of roleplaying data, Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context length. It outperforms existing ~13B models, delivering enhanced roleplaying capabilities." Note: Took me a bit to get into it as I've been busy with life things but this model has performed amazingly well so far. Even the formatting is more stable than others when it comes to asterisks. Not perfect, but close. SillyTavern: Use the Llama-3 presets (simple) or Virt's amazing roleplay presets here (recommended) with the Simple samplers. If you have questions, please do ask. Support: My upload speeds have been cooked and unstable lately. Realistically I'd need to move to get a better provider. If you want and you are able to... You can support my various endeavors here (Ko-fi). I apologize for disrupting your experience. !image/png
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Llama-3-Soliloquy-8B-v2-F16.gguf | GGUF | F16 | 14.97 GB | Download |
| Llama-3-Soliloquy-8B-v2-IQ3_M-imat.gguf | GGUF | IQ3_M | 3.52 GB | Download |
| Llama-3-Soliloquy-8B-v2-IQ3_S-imat.gguf | GGUF | IQ3_S | 3.43 GB | Download |
| Llama-3-Soliloquy-8B-v2-IQ3_XXS-imat.gguf | GGUF | IQ3_XXS | 3.05 GB | Download |
| Llama-3-Soliloquy-8B-v2-IQ4_NL-imat.gguf | GGUF | IQ4_NL | 4.36 GB | Download |
| Llama-3-Soliloquy-8B-v2-IQ4_XS-imat.gguf | GGUF | IQ4_XS | 4.14 GB | Download |
| Llama-3-Soliloquy-8B-v2-Q4_K_M-imat.gguf | GGUF | Q4_K_M | 4.58 GB | Download |
| Llama-3-Soliloquy-8B-v2-Q4_K_S-imat.gguf | GGUF | Q4_K_S | 4.37 GB | Download |
| Llama-3-Soliloquy-8B-v2-Q5_K_M-imat.gguf | GGUF | Q5_K_M | 5.34 GB | Download |
| Llama-3-Soliloquy-8B-v2-Q5_K_S-imat.gguf | GGUF | Q5_K_S | 5.21 GB | Download |
| Llama-3-Soliloquy-8B-v2-Q6_K-imat.gguf | GGUF | Q6_K | 6.14 GB | Download |
| Llama-3-Soliloquy-8B-v2-Q8_0-imat.gguf | GGUF | — | 7.95 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "cc-by-nc-sa-4.0",
"tags": [
"roleplay",
"gguf"
],
"frontmatter": {
"license": "cc-by-nc-sa-4.0",
"tags": [
"roleplay",
"gguf"
]
},
"hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/u98dnnRVCwMh6YYGFIyff.png",
"summary": "Originally these were my personal GGUF-IQ-Imatrix quants of **openlynn/Llama-3-Soliloquy-8B-v2**. Read the original model page for details. **Author:** \"Soliloquy-L3 is a highly capable roleplaying model designed for immersive, dynamic experiences. Trained on over 250 million tokens of roleplaying data, Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context length. It outperforms existing ~13B models, delivering enhanced roleplaying capabilities.\" > [!NOTE] > **Note:** > Took me a bit to get into it as I've been busy with life things but this model has performed amazingly well so far. Even the formatting is more stable than others when it comes to asterisks. Not perfect, but close. > [!WARNING] > **SillyTavern:** > Use the **Llama-3 presets (simple)** or **Virt's amazing roleplay presets here (recommended)** with the Simple samplers. If you have questions, please do ask. > [!TIP] > **Support:** > My upload speeds have been cooked and unstable lately. > Realistically I'd need to move to get a better provider. > If you **want** and you are able to... > **You can support my various endeavors here (Ko-fi).** > I apologize for disrupting your experience. !image/png",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: cc-by-nc-sa-4.0\ntags:\n- roleplay\n- gguf\n---\nOriginally these were my personal GGUF-IQ-Imatrix quants of [**openlynn/Llama-3-Soliloquy-8B-v2**](https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v2). <br>\nRead the original model page for details.\n\n**Author:** <br>\n\"Soliloquy-L3 is a highly capable roleplaying model designed for immersive, dynamic experiences. Trained on over 250 million tokens of roleplaying data, Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context length. It outperforms existing ~13B models, delivering enhanced roleplaying capabilities.\"\n\n> [!NOTE]\n> **Note:** <br>\n> Took me a bit to get into it as I've been busy with life things but this model has performed amazingly well so far. Even the formatting is more stable than others when it comes to asterisks. Not perfect, but close.\n\n> [!WARNING]\n> **SillyTavern:** <br>\n> Use the [**Llama-3 presets (simple)**](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [**Virt's amazing roleplay presets here (recommended)**](https://huggingface.co/Virt-io/SillyTavern-Presets) with the Simple samplers. If you have questions, please do ask.\n\n> [!TIP]\n> **Support:** <br>\n> My upload speeds have been cooked and unstable lately. <br>\n> Realistically I'd need to move to get a better provider. <br>\n> If you **want** and you are able to... <br>\n> [**You can support my various endeavors here (Ko-fi).**](https://ko-fi.com/Lewdiculous) <br>\n> I apologize for disrupting your experience.\n\n\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"roleplay",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"region:us"
],
"likes": 18,
"downloads": 144,
"gated": false,
"private": false,
"last_modified": "2024-05-07T02:07:48.000Z",
"created_at": "2024-05-05T23:53:47.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "66381c0b362d1be0209d3be2",
"id": "Lewdiculous/Llama-3-Soliloquy-8B-v2-GGUF-IQ-Imatrix",
"modelId": "Lewdiculous/Llama-3-Soliloquy-8B-v2-GGUF-IQ-Imatrix",
"sha": "3ba8768678d3f6c2f09590602b9f104281763a9b",
"createdAt": "2024-05-05T23:53:47.000Z",
"lastModified": "2024-05-07T02:07:48.000Z",
"author": "Lewdiculous",
"downloads": 144,
"likes": 18,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 16
}