models_config.json

{
  "repositories": [
    {
      "name": "Unsloth - Qwen3 4B",
      "repo_id": "unsloth/Qwen3-4B-Instruct-2507-GGUF",
      "models": [
        {
          "name": "Qwen3 4B IQ4_XS",
          "filename": "en3-4B-Instruct-2507-IQ4_XS.gguf",
          "description": "4-bit quantization. Very slow on CPU (free CPU inference not recommended)."
        }
      ]
    },
    {
      "name": "HuggingFace TB - SmolLM2 1.7B",
      "repo_id": "HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF",
      "models": [
        {
          "name": "SmolLM2 1.7B Q4_K_M",
          "filename": "smollm2-1.7b-instruct-q4_k_m.gguf",
          "description": "Lightweight 1.7B parameter model, fast inference (Recommended)"
        }
      ]
    },
    {
      "name": "Unsloth - Qwen3 1.7B",
      "repo_id": "unsloth/Qwen3-1.7B-GGUF",
      "models": [
        {
          "name": "Qwen3 1.7B IQ4_XS",
          "filename": "Qwen3-1.7B-IQ4_XS.gguf",
          "description": "Good balance between performance and speed"
        }
      ]
    }
  ]
}