{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreieglf4ek7y5udnmimqzfub7ayqp2vxpsls62uipexsr5n7jq7gzwy",
    "uri": "at://did:plc:mz7h4r2iyp2egghuqaolnsev/app.bsky.feed.post/3mh4w7bxc2gb2"
  },
  "path": "/apps/ios/productivity/noemaai",
  "publishedAt": "2026-03-15T20:25:31.000Z",
  "site": "https://applevis.com",
  "textContent": "Run powerful local AI on iPhone, Mac and visionOS with Noema 2.0, now with Relay, multimodal vision, richer tools, global languages and full offline privacy.\n\nNoema brings large-language-model intelligence to all your devices, fully offline. Download lightweight models directly from Hugging Face and pair them with curated textbooks and your own PDFs. The privacy-first design means your data never leaves your device, whether you are on iPhone, Mac, or visionOS.\n\n- Native macOS app: Run the full Noema experience on your desktop with a rebuilt interface that feels at home on macOS.\n- VisionOS support: Use Noema in spatial computing environments, with windows you can place around your workspace.\n- Noema Relay: Connect your iPhone to your Mac via CloudKit, with no local Wi-Fi required, so one device can host a model while another becomes the client.\n- Vision support for models: Attach photographs to your prompts and use multimodal models for on-device image understanding and analysis.\n- Open Textbook Library integration: Browse and import entire textbooks from OTL through the built-in Explore view; Noema indexes them locally so you can search and retrieve relevant passages on demand.\n- Bring your own data: Add personal documents in PDF or EPUB formats, which are embedded and indexed on-device to power retrieval-augmented generation.\n- Integrated Hugging Face search: Discover and install any quantized model from the Hugging Face hub, with one-tap installation, automatic dependency management, and real-time download progress.\n- RAM check and model size helper: A built-in advisor estimates each model’s memory footprint and shows a badge when it fits your device’s budget; it can also compute the maximum context length that fits in RAM.\n- Triple-backend support: Run models in GGUF, MLX or Liquid AI’s Leap format, so you can choose between high-performance quantized models, Apple-optimised MLX models, and Liquid AI’s lightweight SLMs.\n- Low-RAM, high-knowledge advantage: Noema shifts knowledge into compact datasets rather than bloated weights, allowing larger knowledge bases on low-memory devices.\n- Advanced settings for power users: Fine-tune context length, quantization and GPU acceleration; enable tool-calling for built-in search and other functions; and customise model parameters for optimal performance.\n- Built-in tool calling and RAG: Use integrated search tools and retrieval-augmented generation to query your data without hitting context limits.\n- Localization upgrades: Experience Noema in 10 languages, so international teams can work in the interface that suits them best.\n- Private and offline: All processing happens locally, and your conversations and files never leave the device.",
  "title": "NoemaAI"
}