mudler/mistral-small-4-119b-2603-apex-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": "mistralai/Mistral-Small-4-119B-2603",
    "tags": [
      "gguf",
      "quantized",
      "apex",
      "moe",
      "mixture-of-experts",
      "mistral",
      "mla",
      "vlm",
      "vision"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": "mistralai/Mistral-Small-4-119B-2603",
      "tags": [
        "gguf",
        "quantized",
        "apex",
        "moe",
        "mixture-of-experts",
        "mistral",
        "mla",
        "vlm",
        "vision"
      ]
    },
    "hero_image_url": "",
    "summary": "**APEX (Adaptive Precision for EXpert Models)** quantizations of Mistral-Small-4-119B-2603. **Brought to you by the LocalAI team** | APEX Project | Technical Report",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model: mistralai/Mistral-Small-4-119B-2603\ntags:\n  - gguf\n  - quantized\n  - apex\n  - moe\n  - mixture-of-experts\n  - mistral\n  - mla\n  - vlm\n  - vision\n---\n\n# Mistral-Small-4-119B APEX GGUF\n\n**APEX (Adaptive Precision for EXpert Models)** quantizations of [Mistral-Small-4-119B-2603](https://huggingface.co/mistralai/Mistral-Small-4-119B-2603).\n\n**Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team** | [APEX Project](https://github.com/mudler/apex-quant) | [Technical Report](https://github.com/mudler/apex-quant/blob/main/paper/APEX_Technical_Report.pdf)\n\n## Benchmark Results\n\nBenchmarks coming soon. For reference APEX benchmarks on the Qwen3.5-35B-A3B architecture, see [mudler/Qwen3.5-35B-A3B-APEX-GGUF](https://huggingface.co/mudler/Qwen3.5-35B-A3B-APEX-GGUF).\n\n## Available Files\n\n| File | Profile | Size | Best For |\n|------|---------|------|----------|\n| Mistral-Small-4-119B-APEX-I-Balanced.gguf | I-Balanced | ~72 GB | Best overall quality/size ratio |\n| Mistral-Small-4-119B-APEX-I-Quality.gguf | I-Quality | ~62 GB | Highest quality with imatrix |\n| Mistral-Small-4-119B-APEX-Quality.gguf | Quality | ~62 GB | Highest quality standard |\n| Mistral-Small-4-119B-APEX-Balanced.gguf | Balanced | ~72 GB | General purpose |\n| Mistral-Small-4-119B-APEX-I-Compact.gguf | I-Compact | ~48 GB | Multi-GPU setups, best quality/size |\n| Mistral-Small-4-119B-APEX-Compact.gguf | Compact | ~48 GB | Multi-GPU setups |\n| Mistral-Small-4-119B-APEX-I-Mini.gguf | I-Mini | ~38 GB | Smallest viable |\n| mmproj.gguf | Vision projector | ~827 MB | Required for image understanding |\n\n## What is APEX?\n\nAPEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient -- edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).\n\nSee the [APEX project](https://github.com/mudler/apex-quant) for full details, technical report, and scripts.\n\n## Architecture\n\n- **Model**: Mistral-Small-4-119B-2603 (Mistral4/DeepSeek-V2 style)\n- **Layers**: 36\n- **Experts**: 128 routed + 1 shared (4 active per token)\n- **Total Parameters**: ~119B\n- **Active Parameters**: ~11-12B per token\n- **Attention**: Multi-head Latent Attention (MLA, kv_lora_rank=256, q_lora_rank=1024)\n- **Vision**: Pixtral encoder (mmproj included)\n- **Context**: 1M tokens (YaRN RoPE)\n- **APEX Config**: 5+5 symmetric edge gradient across 36 layers, MLA-aware tensor mapping\n\n## Run with LocalAI\n\n```bash\nlocal-ai run mudler/Mistral-Small-4-119B-2603-APEX-GGUF@Mistral-Small-4-119B-APEX-I-Balanced.gguf\n```\n\n## Credits\n\nAPEX is brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team. Developed through human-driven, AI-assisted research. Built on [llama.cpp](https://github.com/ggerganov/llama.cpp).\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "quantized",
    "apex",
    "moe",
    "mixture-of-experts",
    "mistral",
    "mla",
    "vlm",
    "vision",
    "base_model:mistralai/Mistral-Small-4-119B-2603",
    "base_model:quantized:mistralai/Mistral-Small-4-119B-2603",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1461,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-05T13:25:30.000Z",
  "created_at": "2026-04-05T12:47:28.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69d259e0a11c8adeff5956bb",
  "id": "mudler/Mistral-Small-4-119B-2603-APEX-GGUF",
  "modelId": "mudler/Mistral-Small-4-119B-2603-APEX-GGUF",
  "sha": "3710ec7ca16e602b63af34163907e25238543a7a",
  "createdAt": "2026-04-05T12:47:28.000Z",
  "lastModified": "2026-04-05T13:25:30.000Z",
  "author": "mudler",
  "downloads": 1461,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 10
}