5min chapter

OnTrack: The PCB Design Podcast cover image

Edge Devices and LLMs: What's Ahead for AI

OnTrack: The PCB Design Podcast

CHAPTER

Hyper-Specific LLMs for Niche Applications

This chapter delves into the rise of large language models tailored for specific niches, such as Obsidian with 3 billion parameters, and the potential of deploying such models on edge devices like Linux boxes with limited RAM. It emphasizes the significance of language models with billions of parameters in generating human-readable, reasoning-driven responses to queries within specialized domains, exemplified by their contrast with earlier neural networks in tasks like image identification and metadata assignment.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode