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

strip_debug_info rescue: 0.4.0 debug locations removed (fixes OS 27 beta 2+ load), weights/graph unchanged

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)

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

Document multi-reference in-context editing

Add 2-reference in-context edit transformer (seq 12288)

Document in-context editing (Transformer_edit)

Add in-context edit transformer (512, seq 2048)

Add in-context edit transformer (1024, seq 8192)

Card: mark macOS-only (4B over iPhone memory limit); fix app link to zoo apps/CoreAIImageGen

Remove iOS components (Transformer_512 / VAE *_half): 4B exceeds iPhone memory; macOS-only

Add v0.2 metadata.json descriptor (required by current CoreAIDiffusionPipeline runtime)

add iOS (512/half) component VAEEncoder_half.aimodel

add iOS (512/half) component VAEDecoder_half.aimodel

add iOS (512/half) component Transformer_512.aimodel

FLUX.2 klein 4B: Core AI bundle (macOS, 1024, 4bit)

FLUX.2 klein 4B: Core AI model card

initial commit