#apple silicon
Apple Silicon: 10 AI articles covering apple silicon news, analysis, and research
Articles
Recursive Releases Flint: An Open-Weight 40B MoE Coding Model⭐9
Recursive releases Flint, an open-weight 40B MoE coding model with 2.5B active parameters, Apache 2.0 licensed and built for local agentic coding on 48GB hardwa...
Google Debuts Local-First AI Note-Taker to Challenge Granola⭐8
Google's AI Edge Foresight is a fully offline Mac note-taker with on-device Gemma models, challenging Granola with split-screen notes, transcripts, and a querya...
Apple's New M6 Mac Mini Is Over $100 Off⭐8
Apple's new M6 Mac Mini is over $100 off, now $20 cheaper than the M4 at Best Buy. Save on Apple's latest compact desktop with the M6 chip.
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for⭐8
Liquid AI releases LFM2.5-VL-3B-DSpark, a speculative decoding drafter for its vision-language model, delivering up to 3.13x faster decoding on Apple silicon, w...
Jun Kim, oMLX Creator and Maintainer, Joins Hugging Face to⭐8
Jun Kim, creator of oMLX, joins Hugging Face to support the MLX ecosystem, deepening integration between Apple Silicon MLX models and the Hugging Face Hub.
Apple Might Make Servers Again to Cash In on the AI Rush⭐8
Apple may re-enter server manufacturing to capitalize on the AI boom, potentially using Nvidia tech, reviving its Xserve legacy to challenge data center rivals.
Perplexity Open Sources Lily: A Rust + Metal Inference Engine⭐8
Perplexity open-sources Lily, a Rust and Metal inference engine for Qwen3.6-35B-A3B on Apple Silicon, powering Hybrid Compute with optimized performance.
Perplexity Launches Hybrid Compute on Mac: Cloud Agents Delegate⭐7
Perplexity's hybrid compute on Mac delegates sensitive AI tasks to an on-device model via an open-source privacy gate, ensuring cloud agents protect private fil...
Apple stockpiles inventory as it braces for ‘significant supply⭐8
Apple stockpiles $11.1B in inventory as Tim Cook warns of significant supply constraints from memory shortages, impacting iPhone and Mac production.
How Much Does a Local LLM Actually Cost to Run? I Measured Every⭐9
Measuring real energy costs of local LLMs on Apple Silicon M3 Ultra: 120B model costs 5x less per token than a smaller model, with detailed watt measurements.