Tag
Splish is an unofficial fork of Splash that optimizes Metal kernels for Apple M5 Max chips, delivering up to 1.5× faster AI inference speeds for models like Qwen3.8-27B without compromising quality.
Benchmark results for the Nex-N2.5-mini-MLX-4bit model on Apple M5 Max hardware, achieving 133.6 tokens per second generation speed and quality scores up to 85.80 in research tasks.
Benchmarks on a MacBook Pro M5 Max show that disabling thinking mode in Qwen3.8-27B severely degrades output quality, while xhigh thinking mode uses 5.5x more tokens and runs 6x longer.