Models Optimized for Rapid-MLX Tested & benchmarked MLX models for Rapid-MLX — fastest local AI on Apple Silicon. Tool calling, reasoning, streaming verified. mlx-community/Qwen3.5-4B-MLX-4bit 5B • Updated Mar 2 • 102k • 48 mlx-community/Qwen3.5-9B-4bit Image-Text-to-Text • 9B • Updated Mar 2 • 24.9k • 21 mlx-community/Qwen3.5-27B-4bit Image-Text-to-Text • 27B • Updated Feb 24 • 3.23k • 50 mlx-community/Qwen3.5-35B-A3B-8bit Image-Text-to-Text • 35B • Updated Feb 24 • 1.68k • 23
Models Optimized for Rapid-MLX Tested & benchmarked MLX models for Rapid-MLX — fastest local AI on Apple Silicon. Tool calling, reasoning, streaming verified. mlx-community/Qwen3.5-4B-MLX-4bit 5B • Updated Mar 2 • 102k • 48 mlx-community/Qwen3.5-9B-4bit Image-Text-to-Text • 9B • Updated Mar 2 • 24.9k • 21 mlx-community/Qwen3.5-27B-4bit Image-Text-to-Text • 27B • Updated Feb 24 • 3.23k • 50 mlx-community/Qwen3.5-35B-A3B-8bit Image-Text-to-Text • 35B • Updated Feb 24 • 1.68k • 23
