Add root config.json (Hub download-stats query file + framework pointer)

head-quant docs: per-block-32 absmax ship shape (per-channel = beta delegate bug; naming note)

Upload folder using huggingface_hub

gpu-pipelined int8lin bundle: 253 tok/s M4 Max / 38-39.6 iPhone 17 Pro, oracle gate 16/16

LFM2.5-1.2B Core AI: card + LFM Open License v1.0

initial commit