

Pretty sure they’ve been handing out life jackets to the rich and famous for a while now.


Pretty sure they’ve been handing out life jackets to the rich and famous for a while now.


Trying to escape your captors is normal response.


Yea the EU doing sovereign data centers and sovereign AI (Mistral) is great. Gives me hope maybe I could emigrate with the skills I have.


It’s not just about trust but if access was suddenly cut off they may not be able to pivot as quickly as needed to a US based platform. Also it’s entirely reasonable to expect these tools to be able to analyze the environment they run and determine, invisibly to the user, to decide to set up a backdoor. I mean who is actually reviewing the vibe coded bs?


Your emotions are legitimate.
What are you wanting to do with the model?
Agentic development with that setup, you can easily run a good quant of Qwen3.6-27B at full context. unsloth/Qwen3.6-27B-MTP Q5_K_XL and use a fixed template
Creative writing? Probably need a different model. I’ve heard good things about Gemma 4 31B.
Both of those are dense models so won’t be as fast as Qwen3.6-35B-A3B. Also play around with MTP, quants, KV cache quant, KV caching, etc.
The RAM size will limit you on larger models unless you stream from storage.


I’ve been hoping they would release a refreshed 27b model. 3.6-27b has been my daily workhorse for personal projects.
So, guys, I’ve had a pretty great experience with GMail, from a small company… they index the Internet, whatever that means. Anyway, the sign up is free and and I don’t have to bring a domain… again, not sure what that means, but it sounds nice.