Tech Apr 25, 2026 11 min Running a Non-Qwen MoE on SwiftLM: Ling-flash-2.0 MXFP4 on M1 Max 64GB Feeding inclusionAI's Ling-flash-2.0 (bailing_moe, 100B / 6.1B active, MXFP4 quantization) into SwiftLM on an M1 Max 64GB. Covers the mlx-swift-lm bailing_moe and MXFP4 support check, the startup surprise, and what --stream-experts actually does. Apple Silicon LLM MLX Local LLM Swift SwiftLM MoE MXFP4 Ant Group Experiment
