Card: macOS/iOS 27 GA wording (beta requirement dropped; beta findings dated)

Card: DeviceMark row (2026-09)

Card: definition line (Core AI, 2026-09)

Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes)

Link the card back to its collection and the request box

Add config.json so the Hub can count downloads

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure)

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure)

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure)

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure)

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure)

drop superseded zimage_encoder_seq64_full_bf16.aimodel (bf16 IO; shipped graphs are --io-fp32)

drop superseded zimage_dit_512_cap32_full_native_bf16_dyncap_dynimg.aimodel (bf16 IO; shipped graphs are --io-fp32)

card: measured 256/512/1024 numbers

add tokenizer

add glue

add zimage_encoder_seq64_full_bf16_ids_iofp32.aimodel

add zimage_dit_512_cap32_full_native_bf16_dyncap_dynimg_iofp32.aimodel

add zimage_vae_1024_fp32.aimodel

add zimage_vae_512_fp32.aimodel

add zimage_vae_256_fp32.aimodel

add zimage_encoder_seq64_full_bf16.aimodel

add zimage_dit_512_cap32_full_native_bf16_dyncap_dynimg.aimodel

Upload README.md with huggingface_hub

initial commit