# RTX 4090 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/rtx-4090
> Markdown URL: https://aitinkerers.org/technologies/rtx-4090.md
> Technology record last updated: 2026-05-02T22:33:50Z
> Generated: 2026-09-22T06:52:39Z

The flagship Ada Lovelace GPU: delivering ultimate 4K gaming and AI-accelerated performance with 16,384 CUDA Cores and 24 GB of GDDR6X memory.

This is the NVIDIA GeForce RTX 4090, the ultimate enthusiast GPU built on the Ada Lovelace architecture. It features 16,384 CUDA Cores, 128 RT Cores (3rd-Gen), and 512 Tensor Cores (4th-Gen) for massive compute power. The card is configured with 24 GB of high-speed GDDR6X VRAM on a 384-bit bus, providing approximately 1 TB/s of bandwidth. Expect unmatched 4K performance: DLSS 3 with Frame Generation delivers up to 4X the brute-force rendering speed. Launched at a $1,599 MSRP, this 450W TGP powerhouse sets the definitive standard for high-end gaming and professional creative workflows.

- Official technology site: https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4090/
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building a Product Powered by Local LLM's Only - Using LLM's in Cursor](https://seattle.aitinkerers.org/talks/rsvp_mXEnxibIEu8)

I wanted to describe my journey that started about 5 months ago upon my first AI Tinkerers event where I was curious to work with LLM's but didn't really know how to get started. After my first event, I got advice to use LM Studio to play with local LLM's to create. I was instantly hooked, but I wanted to put them to work in a way other's hadn't in a privacy sensitive way, using Locally hosted LLM's only. To learn, I had to get creative, and I wanted to use LLM's to help build it in a language I'm not as proficint in, Python. This started an multi-month journey into building games to guess who's a murderer to building a bot that uses Experience Sampling Method (ESM) to capture real-time, contextual data about how people feel during different activities, avoiding the biases of memory recall. The talk will talk about my journey to build the app, the types of things people run into, including dropping $2k on an RTX 4090 Super.

- Event context: AI Tinkerers Seattle - February 2025 Meetup — 2025-02-22 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_mXEnxibIEu8

## Related Technologies

- [LM Studio](https://aitinkerers.org/technologies/lm-studio) ([Markdown](https://aitinkerers.org/technologies/lm-studio.md)) — 8 public demos
- [Local LLMs](https://aitinkerers.org/technologies/local-llms) ([Markdown](https://aitinkerers.org/technologies/local-llms.md)) — 2 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [WhatsApp](https://aitinkerers.org/technologies/whatsapp) ([Markdown](https://aitinkerers.org/technologies/whatsapp.md)) — 9 public demos