Search

1 result for “Per-Layer Embeddings”

Technology 09 Aug 2026

slvDev Runs 28.9M-Parameter LLM at 9.88 Tokens/Second on $10 ESP32-S3 Microcontroller

Developer slvDev runs a 28.9M-parameter LLM at 9.88 tokens/sec on a $10 ESP32-S3 microcontroller using 4-bit quantization and Per-Layer Embeddings from Google's Gemma 3n to fit the model in flash storage.