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

Upload README.md with huggingface_hub

card: gpu-pipelined int8lin bundle (iPhone 50.3-51.5 / Mac 204 tok/s) + run instructions

qwen3.5-0.8B int8lin decode-only loop-free bundle (pipelined engine): Mac 204 tok/s, iPhone 50.3-51.5 tok/s

int8 fused-kernel monolith (42.5-45.4 tok/s) + q16 chunked-prefill companion (147 tok/s) — new release config

ios-gpu: add qwen3_5_0_8b_ios_hc_prefill_q16_b2048_int8.aimodel

ios-gpu: add qwen3_5_0_8b_ios_hc0_int8v3.aimodel

Remove pre-category-layout path ios-gpu-static/

Remove pre-category-layout path dynamic-int8/

macOS GPU best: dynamic int8 (58.5 tok/s release)

iOS ANE best: dynamic int8 (14.7 tok/s)

iOS GPU best: fp16 static ctx-2048 monolith (27.7 tok/s)

Card: category layout (best verified config per platform x compute-unit)

static ctx-2048 monolith (iPhone GPU 27.7 tok/s, release config)

dynamic int8 bundle (iPhone GPU 12.5 / ANE 14.7 / Mac 58.5 tok/s)

Model card

initial commit