Local LLMs: From Hype to Hardware - An Open Roundtable

### Local LLMs: From Hype to Hardware - An Open Roundtable

Product Foundry.AI

Event Description:
Are you running language models on your own machine? Or are you tired of API fees and curious about what it really takes to run powerful AI locally?

This isn't your typical presentation. This is a hands-on, open roundtable discussion for everyone interested in the burgeoning world of local Large Language Models. We're calling on the experts, the tinkerers, and the deeply curious to come together for a dynamic session on what works, what doesn't, and what's next.

Who is this for?

• The Practitioners & Experts: If you're already running models like Llama 3, Mistral, or Phi-3 on your own hardware, we want your insights! Come share your setup, your successes, and your war stories.
• The Curious & Aspiring: If you've heard about local LLMs but don't know where to start, this is the perfect place to learn from those on the front lines. Come listen, ask questions, and get a real-world understanding of the landscape.

Format:
This will be a facilitated group discussion, not a one-way lecture. We'll have a moderator to guide the conversation around key themes, but the floor will be open for experts to share their input and for everyone to ask questions. Expect a lively, interactive, and highly informative session.
Potential Discussion Points:

• The Hardware Hurdle: What GPUs are people actually using? Is a Mac Studio enough? Let's talk about VRAM, quantization, and getting the most bang for your buck.
• Models & Matchups: Which models excel at coding vs. creative writing? What are the trade-offs between model size and performance?
• Tools of the Trade: A look at popular tools like Ollama, LM Studio, Jan, and others for running and managing models.
• Real-World Use Cases: What are you building with local LLMs? We want to hear about your RAG pipelines, agentic workflows, and custom applications.
• The Failure File: What have you tried that just didn't work? Let's talk about the limitations, the frustrating dead-ends, and the current boundaries of local AI.

What You'll Learn:

• Practical, no-nonsense advice on getting started with local LLMs.
• An understanding of the current ecosystem of models and tools.
• Connections with other local AI enthusiasts and experts in the community.

Come with your questions, bring your expertise, and let's figure this out together. RSVP now!