Local, Cloud, API, or Subscription? Choosing the Right AI for Your Profile

A masterclass on estimating which models each hardware setup can run, and at what speed, so you can make informed decisions based on your profile, budget, privacy requirements, and performance needs

September 17, 2026 11:00 AM

PST

Live Webinar

Register Now

Panelists

Felipe Gené de Faria

Sr. Serverless Developer

Working with Serverless since 2019. Lambda Custom envs, Lambda Containers, Node.js, Golang, and FOSS Contributing are my favorite hobbies.

What will you learn?

1

LLM in a Nutshell

Understand a lot of the current Alphabet Soup we have in this field that might seem intimidating ( Q4_K_M, MTP, 35BA3B etc )

2

Learn about your profile

Identify what models are the right ones for you without over spending

3

Live Demo

Example of a local LLM running on regular consumer hardware with good performance, all backed up by the calculations we learned during the show

We're not just serverless enthusiasts, we're Serverless Gurus

We collaborate with Fortune 100+ companies, guiding them to understand, adopt, and transition into the serverless world. Our expertise lies in empowering existing developers to be effective with serverless technologies, ensuring your team can fully leverage its potential.

Secure Your Seat!

A masterclass on estimating which models each hardware setup can run, and at what speed, so you can make informed decisions based on your profile, budget, privacy requirements, and performance needs

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.