https://swifttribune.walidsassi.com/tags/local-llm/Recent content in Local LLM on SwiftTribunehttps://swifttribune.walidsassi.com/images/og-default.svghttps://swifttribune.walidsassi.com/images/og-default.svgHugo -- 0.147.8en-usSun, 17 May 2026 00:00:00 +0000https://swifttribune.walidsassi.com/podcast/mlx-swift-on-device-ai-adrien-grondin/Sun, 17 May 2026 00:00:00 +0000https://swifttribune.walidsassi.com/podcast/mlx-swift-on-device-ai-adrien-grondin/Adrien Grondin on MLX Swift, running Mistral, Qwen and Gemma locally on Apple Silicon, how MLX differs from Core ML and Foundation Models, and the real limits of on-device inference: memory, battery, latency.