Running the Qwen 3.8 27B UD-Q4_K_XL on my RTX 4090 and I’m just mind blown.
This is THE BEST local AI model we’ve ever seen. Insane agentic coding capabilities. Great work Alibaba_Qwen
We can now run an Opus 4.6 level model at home for $0.
Qwen 3.8 27B is seriously impressive for an open weight model. Six months ago, Claude Opus 4.6 was my main driver, and I was spending a lot of money on it. Today, I can run a model at this level for free on my laptop. Qwen
Breville 920 = Qwen3.8-27b
In the coffee machine world, the Breville 920 is on the same level as the Qwen 3.8-27b. Everyone, take a moment to relax.
This is Qwen 3.8 27B in the pi harness with oh-my-pi extension.
The trees and extra elements are much richer than vanilla pi but the pagoda is floating. The birds are a nice touch. oh-my-pi used 145k tokens (6.5x more than vanilla pi!) over 85 turns!
You have reached the end of the archive
All of qwen38