“Google AI Edge Foresight for Mac turns scribbles into full notes using offline recordings”

Key points

• Google released EmbeddingGemma 2, a 740M parameter model for on-device use.
• The model runs locally with low memory: ~191MB for text, ~567MB for multimodal.
• Demonstrations include Android and iOS via AI Edge Gallery; Mac app showcased.
• AI Edge Foresight aggregates shorthand notes into polished notes from transcripts.
• App supports local files, Google Drive, and conversational retrieval with personal knowledge.