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

Vytvořeno 7d | 30. 5. 2025 12:50:06

Chcete-li přidat komentář, přihlaste se

Ostatní příspěvky v této skupině

Weaponizing Dependabot: Pwn Request at its finest

Article URL: https://boostsecurity.io/blog/weaponizing-dependabot-pwn-request-at-its-finest

Comm

6. 6. 2025 14:10:09 | Hacker news

Swift and Cute 2D Game Framework: Setting Up a Project with CMake

Article URL: https://layer22.com/swift-and-cute-framework-setting-up-a-project-with-cmake

Comments

6. 6. 2025 14:10:08 | Hacker news

Editing astrophotography

Article URL: https://astroimagery.com/techniques/post-processing/how-to-edit-astrophotography-

6. 6. 2025 14:10:08 | Hacker news

Doge Developed Error-Prone AI Tool to "Munch" Veterans Affairs Contracts

Article URL: https://www.propublica.org/article/trump-doge-veterans-affairs-ai-contracts-health-ca

6. 6. 2025 14:10:06 | Hacker news

Dystopian tales of that time when I sold out to Google

Article URL: https://wordsmith.social/elilla/deep-in-mordor-where-the-shado

6. 6. 2025 14:10:06 | Hacker news

Small Programs and Languages

Article URL: https://ratfactor.com/cards/pl-small

Comments URL: https://news.ycomb

6. 6. 2025 14:10:04 | Hacker news

A masochist's guide to web development

Article URL: https://sebastiano.tronto.net/blog/2025-06-06-webdev/

Comments URL:

6. 6. 2025 14:10:03 | Hacker news

Techie