Developer builds 20ms real-time embedding endpoint with EmbeddingGemma 2 on MacBook CPU

Developer mmastrac demonstrated a real-time embedding endpoint built on Google's EmbeddingGemma 2, achieving roughly 20ms for text and 100ms for image embeddings while running entirely on a MacBook CPU.

2026-10-27 ~ 2026-10-28 · 2 related posts

• EmbeddingGemma2 powers a 20ms real-time endpoint in this dev's Jev project — bodonoghue85 · 2026-10-27
• EmbeddingGemma 2 runs real-time embeddings on a MacBook CPU alone: 20ms text, 100ms images — generativist · 2026-10-28