lewdiculous/poppy_porpoise-v0.7-l3-8b-gguf-iq-imatrix F16 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
lewdiculous/poppy_porpoise-v0.7-l3-8b-gguf-iq-imatrix overview
If you want to use vision functionality: You must use the latest versions of Koboldcpp. # To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo. https://huggingface.co/ChaoticNeutrals/Llava_1.5_Llama3_mmproj You can load the mmproj by using the corresponding section in the interface: !image/png
Downloads
346
Likes
29
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
11 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Poppy_Porpoise-v0.7-L3-8B-F16.gguf | GGUF | F16 | 14.97 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-IQ3_M-imat.gguf | GGUF | IQ3_M | 3.52 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-IQ3_XXS-imat.gguf | GGUF | IQ3_XXS | 3.05 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-IQ4_NL-imat.gguf | GGUF | IQ4_NL | 4.36 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-IQ4_XS-imat.gguf | GGUF | IQ4_XS | 4.14 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-Q4_K_M-imat.gguf | GGUF | Q4_K_M | 4.58 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-Q4_K_S-imat.gguf | GGUF | Q4_K_S | 4.37 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-Q5_K_M-imat.gguf | GGUF | Q5_K_M | 5.34 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-Q5_K_S-imat.gguf | GGUF | Q5_K_S | 5.21 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-Q6_K-imat.gguf | GGUF | Q6_K | 6.14 GB | Download |
| Poppy_Porpoise-v0.7-L3-8B-Q8_0-imat.gguf | GGUF | — | 7.95 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"tags": [
"roleplay",
"llama3",
"sillytavern"
],
"language": [
"en"
],
"frontmatter": {
"tags": [
"roleplay",
"llama3",
"sillytavern"
],
"language": [
"en"
]
},
"hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/v6AZmbk-Cb52KskTQTwzW.png",
"summary": "If you want to use vision functionality: * You must use the latest versions of Koboldcpp. # To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. https://huggingface.co/ChaoticNeutrals/Llava_1.5_Llama3_mmproj * You can load the **mmproj** by using the corresponding section in the interface: !image/png",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\ntags:\n- roleplay\n- llama3\n- sillytavern\nlanguage:\n- en\n---\n> [!CAUTION]\n> **New and improved version here:** <br>\n> Prefer the new [**version 0.72 here!**](https://huggingface.co/Lewdiculous/Poppy_Porpoise-0.72-L3-8B-GGUF-IQ-Imatrix)\n\n> [!TIP]\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**\"It keeps getting better!\"**\n\n\"One of the top recent performers in the **Chaiverse Leaderboard**!\"\n\nGGUF-IQ-Imatrix quants for [ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B).\n\n> [!IMPORTANT] \n> **Updated!**\n> These quants have been redone with the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920) in mind. <br>\n> Use **KoboldCpp version 1.64** or higher.\n\n> [!WARNING]\n> Compatible SillyTavern presets [here (recommended/simple)](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets)) or [here (Virt's)](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>\n> Use the latest version of KoboldCpp. **Use the provided presets.** <br>\n> This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now.\n\n> [!NOTE]\n> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes.\n\n**Original model information:**\n\n\n\n# Update: Vision/multimodal capabilities again!\n\n If you want to use vision functionality:\n\n * You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).\n \n# To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. https://huggingface.co/ChaoticNeutrals/Llava_1.5_Llama3_mmproj\n \n * You can load the **mmproj** by using the corresponding section in the interface:\n\n ",
"related_quantizations": []
},
"tags": [
"gguf",
"roleplay",
"llama3",
"sillytavern",
"en",
"endpoints_compatible",
"region:us"
],
"likes": 29,
"downloads": 346,
"gated": false,
"private": false,
"last_modified": "2024-05-06T20:32:32.000Z",
"created_at": "2024-04-24T12:32:05.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6628fbc555d7c289634444ec",
"id": "Lewdiculous/Poppy_Porpoise-v0.7-L3-8B-GGUF-IQ-Imatrix",
"modelId": "Lewdiculous/Poppy_Porpoise-v0.7-L3-8B-GGUF-IQ-Imatrix",
"sha": "325c5db8e94979cf4dc48575da3158841a3d1f60",
"createdAt": "2024-04-24T12:32:05.000Z",
"lastModified": "2024-05-06T20:32:32.000Z",
"author": "Lewdiculous",
"downloads": 346,
"likes": 29,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 15
}