LLamaRecipes/recipes/quickstart/inference/mobile_inference/android_inference/mlc-package-config.json

{
    "device": "android",
    "model_list": [
        {
            "model": "HF://mlc-ai/Llama-3-8B-Instruct-q4f16_1-MLC",
            "estimated_vram_bytes": 4348727787,
            "model_id": "Llama-3-8B-Instruct",
            "overrides": {
                "context_window_size": 768,
                "prefill_chunk_size": 256
            }
        }
    ]
}