macOS 26.2 introduces RDMA over Thunderbolt 5 and the JACCL collective communication library, enabling MLX to shard large language model inference and fine-tuning across multiple Apple Silicon Macs in a cluster. Developers can now run models too large for a single machine or dramatically accelerate token generation by spreading computation across up to N nodes with a single CLI flag.
ā¢ Run trillion-parameter models (e.g., Kimi 2.6 at ~1 TB quantized) that exceed a single machine's memory by distributing weights across multiple Macs connected via Thunderbolt 5
ā¢ Achieve ~3Ć inference throughput for 27B-parameter models on a 4-node cluster compared to a single M3 Ultra, with near-zero code changes using mlx.launch
ā¢ JACCL automatically selects mesh vs. ring topology based on message size, so developers get optimal latency and bandwidth without manual tuning
Foundation Models is a new Apple framework introduced in iOS 27 that gives developers on-device access to the same Apple Intelligence language model powering system features, enabling text generation, structured output, and tool-calling entirely on-device without a network connection.
Visual Intelligence brings iOS 17's Visual Look Up capabilities to a new developer-facing API surface in iOS 27, letting apps pipe live camera frames or static images through on-device scene understanding to extract subjects, text, barcodes, and rich semantic labels without any cloud round-trip.
iOS 27 opens the Foundation Models framework to third-party LLM providers via a new public LanguageModel protocol, enabling anyone to integrate custom, server-based, or open-source models using the same Swift API as Apple's on-device system model.
In-depth guide
iOS 27 On-Device AI & Apple Intelligence āApp Schemas let developers describe their app's content and actions using pre-defined domain schemas (like the Calendar domain) so Siri can understand, search, and act on app data without custom NLP. Entities conforming to IndexedEntity are donated to Spotlight's semantic index, enabling natural-language queries over app content.