Apple Neural Engine LLMs
Collection
CoreML LLMs optimized for Apple Neural Engine. • 3 items • Updated
• 2
CoreML conversion of Llama-3.2-1B-Instruct with a 512 context length. Optimized for Apple Neural Engine.
Use this CLI to download and run inference. macOS 14 (Sonoma) is required.
Base model
meta-llama/Llama-3.2-1B-Instruct