Laya (OS Jev) on Mac M4 CoreML Offline (45 decisions per second)
Summary
The Laya model runs offline on Apple's M4 chip using CoreML, achieving 45 decisions per second in inference.
Similar Articles
@LinQ444: jev 和laya的对比 https://github.com/mizorewww/laya-mlx…
Laya-MLX is an open-weight tool for running typed decision AI models locally on Apple Silicon with low latency, providing native inference without cloud APIs. It includes benchmarks showing fast performance on devices like M3 Max.
@mizorewww: Introducing a version 50 times faster than Jev, running on your device: laya-mlx! Occupies a maximum of 1G memory only …
Introducing laya-mlx, an open-source classification system optimized for Apple Silicon using MLX, which offers 50 times faster performance than Jev with a maximum of 1G memory usage, demonstrated through a real-time Snake game demo.
Laya model playing Flappy Bird on a CPU using OpenVINO INT8 inference
A 421M-parameter Laya model is demonstrated playing Flappy Bird on a desktop CPU using OpenVINO INT8 quantization, showcasing efficient AI inference on consumer hardware.
Optimizing On-Device Inference for Apple Silicon (20 minute read)
Apple's Lily engine optimizes on-device LLM inference for Apple silicon by leveraging unified memory and hardware, outperforming MLX-LM, and is tuned for the Qwen3.6-35B-A3B model's architecture.
Laya the open source version of Jev
Laya is an open-source, fast multilingual decision engine that offers non-autoregressive, calibrated probabilities for structured schemas, claiming to be 6-8 times faster than Jev with full openness.