In this video, we’ll explore the power of running large language models (LLMs) entirely locally on an RTX 5090 GPU. I’ll demonstrate how easily you can use open-source LLMs locally using LM Studio, showcasing models like DeepSeek R1 and GEMMA 3 27B. We’ll dive into various LLM capabilities including text generation, multimodal AI, and even touch on future possibilities of video and image generation. This is Part 2 of a three-part series on the RTX 5090, with today’s focus on LLMs and their local performance on this powerful GPU.
▼ Link(s) From Today’s Video:
Run LLMs Locally for yourself!:
Learn More about RTX 5090:
Check out Part One:
► MattVidPro Discord:
► Follow Me on Twitter:
► Buy me a Coffee!
————————————————-
▼ Extra Links of Interest:
General AI Playlist:
AI I use to edit videos:
Instagram: instagram.com/mattvidpro
Tiktok: tiktok.com/@mattvidpro
Gaming & Extras Channel:
Let’s work together!
– For brand & sponsorship inquiries:
– For all other business inquiries: [email protected]
Thanks for watching Matt Video Productions! I make all sorts of videos here on Youtube! Technology, Tutorials, and Reviews! Enjoy Your stay here, and subscribe!
All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.
00:00 Introduction to Running LLMs Locally
01:27 Setting Up LM Studio
01:58 Testing DeepSeek R1 on RTX 5090
02:42 Exploring Model Settings and Performance
03:48 Generating Content with DeepSeek R1
06:19 Loading Larger Models
09:44 Pushing the Limits with 32B Models
12:47 Reflections on Local AI Performance
16:55 Introduction to GEMMA 327B
17:15 Setting Up the Model
18:00 First Impressions and Performance
18:47 Roasting with GEMMA
22:48 Analyzing Memes and Humor
27:53 Exploring Smaller LLMs
30:49 Conclusion and Future Plans
source
