Neural-Engine on Noureddine RAMDIhttps://ramdi.fr/tags/neural-engine/Recent content in Neural-Engine on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000Orion: Direct access to Apple Neural Engine for on-device LLM traininghttps://ramdi.fr/github-stars/orion-direct-access-to-apple-neural-engine-for-on-device-llm-training/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/orion-direct-access-to-apple-neural-engine-for-on-device-llm-training/Orion bypasses CoreML to access Apple’s Neural Engine directly via private frameworks, enabling on-device inference and fine-tuning of small LLMs with 8.5x reduced training overhead.Running Stable Diffusion locally on Apple Silicon with Mochi Diffusionhttps://ramdi.fr/github-stars/running-stable-diffusion-locally-on-apple-silicon-with-mochi-diffusion/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/running-stable-diffusion-locally-on-apple-silicon-with-mochi-diffusion/Mochi Diffusion runs Stable Diffusion and FLUX.2 Klein models locally on Apple Silicon Macs using Core ML, achieving ~150MB memory usage with fast inference, all offline.