Gamers Nexus

[hog cranking frog]

Does anyone actually use AI agents? Chatbots are handy but agents sound retarded.

Constantly.

I'm very cynical with regards to tech but agents changed my job almost overnight. I type considerably less now which has made my wrist pain go away.

 

[Celebrate Nite]

A possible alternative to thermal paste?

 

[StacticShock]

Steveception over the retardation of ngreedia trying to sell the entire "rent computers" shit plus some AI datacenter potshots, especially since steve mentioned that chinks no longer get freebies from nvidia because of their chinkery.

 

[StacticShock]

7 days later jeettube recommends me that bragstationer met with 史蒂夫(steve in chinkenese) to discuss stuff about the market.

 

[Celebrate Nite]

 

[Post Reply]

The big problem is that one of the very few places LLMs actually make sense is coding, and you can't get away from using these tools at this point. I've heard qwen3.6:35b-a3b has gotten really good and on par with some of the OpenAI models, but it won't run on my 32GB AMD 9700R. Not enough VRAM!

I think you are misunderstanding something. You can run the MoE 35b model with as little as 8gb VRAM and get decent performance. It runs just fine on my 12gb and 16gb cards. If you have 32gb, you should be going one step higher to the dense 27b model, which is distinctly better.