matrixportalx/turkish-llama3-8b-merged-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": [
      "meta-llama/Meta-Llama-3-8B",
      "ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1",
      "ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1"
    ],
    "tags": [
      "merge",
      "mergekit",
      "lazymergekit",
      "meta-llama/Meta-Llama-3-8B",
      "ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1",
      "ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1"
    ],
    "frontmatter": {
      "base_model": [
        "meta-llama/Meta-Llama-3-8B",
        "ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1",
        "ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1"
      ],
      "tags": [
        "merge",
        "mergekit",
        "lazymergekit",
        "meta-llama/Meta-Llama-3-8B",
        "ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1",
        "ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1"
      ]
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model:\n- meta-llama/Meta-Llama-3-8B\n- ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1\n- ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1\ntags:\n- merge\n- mergekit\n- lazymergekit\n- meta-llama/Meta-Llama-3-8B\n- ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1\n- ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1\n---\n\n# Turkish-Llama3-8B-Merged GGUF Quantized Models\n\n## Technical Details\n- **Quantization Tool:** llama.cpp\n- **Version:** ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no\n\n## Model Information\n- **Base Model:** [matrixportal/Turkish-Llama3-8B-Merged](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged)\n- **Quantized by:** [matrixportal](https://huggingface.co/matrixportal)\n\n## Available Files\n| 🚀 Download | 🔢 Type | 📝 Description |\n|------------|---------|---------------|\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q2_k.gguf) | Q2 K | Tiny size, lowest quality (emergency use only) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q3_k_s.gguf) | Q3 K S | Very small, low quality (basic tasks) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q3_k_m.gguf) | Q3 K M | Small, acceptable quality |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q3_k_l.gguf) | Q3 K L | Small, better than Q3_K_M (good for low RAM) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q4_0.gguf) | Q4 0 | Standard 4-bit (fast on ARM) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q4_k_s.gguf) | Q4 K S | 4-bit optimized (good space savings) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q4_k_m.gguf) | Q4 K M | 4-bit balanced (recommended default) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q5_0.gguf) | Q5 0 | 5-bit high quality |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q5_k_s.gguf) | Q5 K S | 5-bit optimized |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q5_k_m.gguf) | Q5 K M | 5-bit best (recommended HQ option) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q6_k.gguf) | Q6 K | 6-bit near-perfect (premium quality) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q8_0.gguf) | Q8 0 | 8-bit maximum (overkill for most) |\n| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.f16.gguf) | F16 | Full precision (maximum accuracy) |\n\n💡 **Q4 K M** provides the best balance for most use cases",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "merge",
    "mergekit",
    "lazymergekit",
    "meta-llama/Meta-Llama-3-8B",
    "ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1",
    "ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1",
    "base_model:meta-llama/Meta-Llama-3-8B",
    "base_model:merge:meta-llama/Meta-Llama-3-8B",
    "base_model:ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1",
    "base_model:merge:ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1",
    "base_model:ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1",
    "base_model:merge:ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 102,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-16T00:32:52.000Z",
  "created_at": "2025-04-15T23:07:39.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67fee6bbb4d2abce5462a3fe",
  "id": "matrixportalx/Turkish-Llama3-8B-Merged-GGUF",
  "modelId": "matrixportalx/Turkish-Llama3-8B-Merged-GGUF",
  "sha": "082709e653f0d9c0d9329d11e09485bfda7ac445",
  "createdAt": "2025-04-15T23:07:39.000Z",
  "lastModified": "2025-04-16T00:32:52.000Z",
  "author": "matrixportalx",
  "downloads": 102,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 15
}