Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms…

Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms per decision on an M5 Pro. Release: https://github.com/FluidInference/FluidUse/releases/tag/v0.2.0 Models: https://huggingface.co/FluidInference/laya-coreml Media This is NOT Jev. Open source. Runs on your laptop. Decides in ~27 ms, about 200× faster than waiting on a hosted LLM. Here it is playing Tetris by itself 👇 https://brainfunctioncollapse.com/laya

Related

• The first model of Laya was created with a single over night training and fine-tuning. It only took 15 hours from training to push the model…

Source: Clem Delangue (X) | 2026-09-21