The 5070ti 16gb even a year after it's initial release is still one of the most compelling options for running local AI, especially in the age of local AI agents like Open Claw and Hermes! This GPU is also an exceptional choice for local video models like LTX and Flux. I go over why this GPU is still an incredible value and the best models to use with this GPU and where it falls short.
Let me know what you think in the comments below!
Rent an nVidia GPU on Vast AI (15% OFF) https://cloud.vast.ai/?ref_id=74601
For sponsorships or collaboration inquiries please contact aifluxcontact@proton.me
Chapters 🎬:
0:00 - intro
0:34 - specifications
2:14 - better than 3090?
2:40 - 24gb 5070ti?
3:16 - hugging face benchmarks
5:05 - nvfp4 quantization on blackwell
5:40 - LTX video models
6:51 - flux 2 dev
7:50 - qwen 3.6 benchmarks
8:48 - ebay pricing
9:50 - conclusion
Choose to Build with AI
Matched to Hermes
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
