With the recent release of google's incredible Gemma 4 model and turbo quant, more gpu's than ever with less than 24gb of vram, are now able to do things that would've required much larger and expensive gpus. This means that GPUs like the nVidia RTX 3080 are now a great affordable option for local AI enthusiasts to run multi-modal modals, vibe coding and agentic assistant models (open claw / hermes) from home.
Tell us what you think in the comments below!
Rent an nVidia GPU on Vast AI (15% OFF) https://cloud.vast.ai/?ref_id=74601
Chapters 🎬:
0:00 - intro
0:58 - big deal for nvidia
2:01 - specs
2:58 - gemma 4 llama.cpp
4:38 - gemma 4 e2b
6:03 - gemma 4 e4b
7:47 - pricing on ebay
8:25 - 20gb 3080 from china
9:40 - using gemma 4
11:18 - conclusion
Choose to Build with AI
Matched to Generative AI
AI Maker Residence 3
The third AI workshop taught by our legendary teacher, Nick Sarafa. This is a full-day hands-on training workshop for purposeful co-creation with AI using Claude Code.
Imagine having access to hundreds of billions of dollars of computing power and knowing exactly how to make it work for you through the power of super intelligence.
◆ Fri 09 Oct 2026◆ KOKO Cafe, London◆ With Nick Sarafa
