PulseAugur
EN
LIVE 00:40:08

Developer runs 28.9M parameter LLM on ESP32 microcontroller

By PulseAugur Editorial · [1 sources] ·

A developer known as slvDev has successfully run a large language model with 28.9 million parameters on an ESP32 microcontroller. This achievement is significant because it demonstrates the capability of running such models on low-power, inexpensive hardware without relying on cloud servers. The model operates at approximately 9.5 tokens per second, a notable performance for its parameter count on similar hardware. AI

IMPACT Shows potential for edge AI and on-device LLM inference, reducing reliance on cloud infrastructure.

RANK_REASON Demonstrates a research milestone in running LLMs on low-power hardware. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Developer runs 28.9M parameter LLM on ESP32 microcontroller

COVERAGE [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    MakeUseOf: I didn’t think an ESP32 could run an LLM — until it did. “A developer going by slvDev shipped a project that runs a 28.9-million-parameter model on t

    MakeUseOf: I didn’t think an ESP32 could run an LLM — until it did. “A developer going by slvDev shipped a project that runs a 28.9-million-parameter model on the same class of $8 chip, at around 9.5 tokens per second, with nothing sent to a server. That’s roughly a hundred times…

RELATED ENTITIES

RELATED TOPICS