Model Intelligence Sheet
tensorblock/samantha2.0-qwen2.5-14b-ita-v2-16bit-gguf overview
Website Twitter Discord GitHub Telegram
Downloads
247
Likes
0
Pipeline
text-generation
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "WasamiKirua/Samantha2.0-Qwen2.5-14B-ita-v2-16bit",
"language": [
"en"
],
"license": "apache-2.0",
"tags": [
"text-generation-inference",
"transformers",
"unsloth",
"qwen2",
"trl",
"sft",
"psychology",
"EQ",
"conversational",
"NLP",
"companion",
"TensorBlock",
"GGUF"
],
"pipeline_tag": "text-generation",
"datasets": [
"WasamiKirua/Samantha2.0-ITA",
"WasamiKirua/haiku-ita-v0.2"
],
"frontmatter": {
"base_model": "WasamiKirua/Samantha2.0-Qwen2.5-14B-ita-v2-16bit",
"language": [
"en"
],
"license": "apache-2.0",
"tags": [
"text-generation-inference",
"transformers",
"unsloth",
"qwen2",
"trl",
"sft",
"psychology",
"EQ",
"conversational",
"NLP",
"companion",
"TensorBlock",
"GGUF"
],
"pipeline_tag": "text-generation",
"datasets": [
"WasamiKirua/Samantha2.0-ITA",
"WasamiKirua/haiku-ita-v0.2"
]
},
"hero_image_url": "https://i.imgur.com/jC7kdl8.jpeg",
"summary": "    ",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: WasamiKirua/Samantha2.0-Qwen2.5-14B-ita-v2-16bit\nlanguage:\n- en\nlicense: apache-2.0\ntags:\n- text-generation-inference\n- transformers\n- unsloth\n- qwen2\n- trl\n- sft\n- psychology\n- EQ\n- conversational\n- NLP\n- companion\n- TensorBlock\n- GGUF\npipeline_tag: text-generation\ndatasets:\n- WasamiKirua/Samantha2.0-ITA\n- WasamiKirua/haiku-ita-v0.2\n---\n\n<div style=\"width: auto; margin-left: auto; margin-right: auto\">\n<img src=\"https://i.imgur.com/jC7kdl8.jpeg\" alt=\"TensorBlock\" style=\"width: 100%; min-width: 400px; display: block; margin: auto;\">\n</div>\n\n[](https://tensorblock.co)\n[](https://twitter.com/tensorblock_aoi)\n[](https://discord.gg/Ej5NmeHFf2)\n[](https://github.com/TensorBlock)\n[](https://t.me/TensorBlock)\n\n\n## WasamiKirua/Samantha2.0-Qwen2.5-14B-ita-v2-16bit - GGUF\n\nThis repo contains GGUF format model files for [WasamiKirua/Samantha2.0-Qwen2.5-14B-ita-v2-16bit](https://huggingface.co/WasamiKirua/Samantha2.0-Qwen2.5-14B-ita-v2-16bit).\n\nThe files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).\n\n## Our projects\n<table border=\"1\" cellspacing=\"0\" cellpadding=\"10\">\n <tr>\n <th colspan=\"2\" style=\"font-size: 25px;\">Forge</th>\n </tr>\n <tr>\n <th colspan=\"2\">\n <img src=\"https://imgur.com/faI5UKh.jpeg\" alt=\"Forge Project\" width=\"900\"/>\n </th>\n </tr>\n <tr>\n <th colspan=\"2\">An OpenAI-compatible multi-provider routing layer.</th>\n </tr>\n <tr>\n <th colspan=\"2\">\n <a href=\"https://github.com/TensorBlock/forge\" target=\"_blank\" style=\"\n display: inline-block;\n padding: 8px 16px;\n background-color: #FF7F50;\n color: white;\n text-decoration: none;\n border-radius: 6px;\n font-weight: bold;\n font-family: sans-serif;\n \">🚀 Try it now! 🚀</a>\n </th>\n </tr>\n\n <tr>\n <th style=\"font-size: 25px;\">Awesome MCP Servers</th>\n <th style=\"font-size: 25px;\">TensorBlock Studio</th>\n </tr>\n <tr>\n <th><img src=\"https://imgur.com/2Xov7B7.jpeg\" alt=\"MCP Servers\" width=\"450\"/></th>\n <th><img src=\"https://imgur.com/pJcmF5u.jpeg\" alt=\"Studio\" width=\"450\"/></th>\n </tr>\n <tr>\n <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>\n <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>\n </tr>\n <tr>\n <th>\n <a href=\"https://github.com/TensorBlock/awesome-mcp-servers\" target=\"_blank\" style=\"\n display: inline-block;\n padding: 8px 16px;\n background-color: #FF7F50;\n color: white;\n text-decoration: none;\n border-radius: 6px;\n font-weight: bold;\n font-family: sans-serif;\n \">👀 See what we built 👀</a>\n </th>\n <th>\n <a href=\"https://github.com/TensorBlock/TensorBlock-Studio\" target=\"_blank\" style=\"\n display: inline-block;\n padding: 8px 16px;\n background-color: #FF7F50;\n color: white;\n text-decoration: none;\n border-radius: 6px;\n font-weight: bold;\n font-family: sans-serif;\n \">👀 See what we built 👀</a>\n </th>\n </tr>\n</table>\n## Prompt template\n\n```\n<|im_start|>system\n{system_prompt}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n```\n\n## Model file specification\n\n| Filename | Quant type | File Size | Description |\n| -------- | ---------- | --------- | ----------- |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q2_K.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q2_K.gguf) | Q2_K | 5.770 GB | smallest, significant quality loss - not recommended for most purposes |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q3_K_S.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q3_K_S.gguf) | Q3_K_S | 6.660 GB | very small, high quality loss |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q3_K_M.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q3_K_M.gguf) | Q3_K_M | 7.339 GB | very small, high quality loss |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q3_K_L.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q3_K_L.gguf) | Q3_K_L | 7.925 GB | small, substantial quality loss |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q4_0.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q4_0.gguf) | Q4_0 | 8.518 GB | legacy; small, very high quality loss - prefer using Q3_K_M |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q4_K_S.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q4_K_S.gguf) | Q4_K_S | 8.573 GB | small, greater quality loss |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q4_K_M.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q4_K_M.gguf) | Q4_K_M | 8.988 GB | medium, balanced quality - recommended |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q5_0.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q5_0.gguf) | Q5_0 | 10.267 GB | legacy; medium, balanced quality - prefer using Q4_K_M |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q5_K_S.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q5_K_S.gguf) | Q5_K_S | 10.267 GB | large, low quality loss - recommended |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q5_K_M.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q5_K_M.gguf) | Q5_K_M | 10.509 GB | large, very low quality loss - recommended |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q6_K.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q6_K.gguf) | Q6_K | 12.125 GB | very large, extremely low quality loss |\n| [Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q8_0.gguf](https://huggingface.co/tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF/blob/main/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q8_0.gguf) | Q8_0 | 15.702 GB | very large, extremely low quality loss - not recommended |\n\n\n## Downloading instruction\n\n### Command line\n\nFirstly, install Huggingface Client\n\n```shell\npip install -U \"huggingface_hub[cli]\"\n```\n\nThen, downoad the individual model file the a local directory\n\n```shell\nhuggingface-cli download tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF --include \"Samantha2.0-Qwen2.5-14B-ita-v2-16bit-Q2_K.gguf\" --local-dir MY_LOCAL_DIR\n```\n\nIf you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:\n\n```shell\nhuggingface-cli download tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'\n```\n",
"related_quantizations": []
},
"tags": [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"sft",
"psychology",
"EQ",
"conversational",
"NLP",
"companion",
"TensorBlock",
"GGUF",
"text-generation",
"en",
"dataset:WasamiKirua/Samantha2.0-ITA",
"dataset:WasamiKirua/haiku-ita-v0.2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"likes": 0,
"downloads": 247,
"gated": false,
"private": false,
"last_modified": "2026-01-27T21:14:28.000Z",
"created_at": "2025-01-02T02:19:48.000Z",
"pipeline_tag": "text-generation",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6775f7c40b23564241bdb3ee",
"id": "tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF",
"modelId": "tensorblock/Samantha2.0-Qwen2.5-14B-ita-v2-16bit-GGUF",
"sha": "a0e516e2104deb374b632081aa35b5d8ca78a5eb",
"createdAt": "2025-01-02T02:19:48.000Z",
"lastModified": "2026-01-27T21:14:28.000Z",
"author": "tensorblock",
"downloads": 247,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "transformers",
"siblings_count": 4
}