Intermediate

Choosing Open-source LLMs

Evaluate open-source LLMs for performance, usability, licensing and practical deployment constraints.

"I'm looking at Llama models, various Mistral options, something called Falcon, and then all these parameter counts — 7B, 13B, 70B. One model requires massive compute power, another runs fine on standard machines but struggles with complex queries, and the third has licensing terms that are hard to understand."

An AI system trained to understand and generate human-like text — a highly sophisticated autocomplete system capable of writing, analyzing, summarizing, and even coding.

Result: analyses take hours, the cloud budget is exhausted in two weeks. Yet a smaller model would have produced similar results for 19th-century poetry analysis.

Sign in to read this course

A free account unlocks all 514 courses. 20 are readable without one.

What's inside

5 sections
  1. 1 Table of Contents
  2. 2 Module 1 — Introduction to Open-source LLMs
  3. 3 Module 2 — Evaluating Models for Performance and Usability
  4. 4 Module 3 — Licenses and Practical Constraints
  5. 5 Appendix — Resources and References

Interested in this course?

Contact us to book it or get a custom training plan for your team.