What is currently the best LLM model for consumer grade hardware? Is it phi-4?

I have a 5060ti with 16GB VRAM. I’m looking for a model that can hold basic conversations, no physics or advanced math required. Ideally something that can run reasonably fast, near real time.


Comments URL: https://news.ycombinator.com/item?id=44134896

Points: 23

# Comments: 10

https://news.ycombinator.com/item?id=44134896

Établi 1d | 30 mai 2025, 12:50:06


Connectez-vous pour ajouter un commentaire

Autres messages de ce groupe

Show HN: AI Peer Reviewer – Multiagent System for Scientific Manuscript Analysis

After waiting 8 months for a journal response or two months for co-author feedback that consisted of "looks good" and a single comma change, we built an AI-powered peer review system that helps re

31 mai 2025, 16:40:17 | Hacker news
Show HN: Fontofweb – Discover Fonts Used on a Website or Websites Using Font(s)

Hey HN, I've been working on fontofweb.com on and off for the past 4 years, and I'm keen to share it with you. It lets you type in the URL of any website and see exactly how the fonts are used: al

31 mai 2025, 16:40:13 | Hacker news
Ask HN: Anyone making a living from a paid API?

Are there any solo devs or small teams out there genuinely paying their rent from selling API access?

What's your API? How much MRR? What's your pricing model? How did you find your first paying

31 mai 2025, 16:40:11 | Hacker news