Built an alternative version of typesafeai but on cerebras with Qwen 3.8 27b.
Similar quality, similar performance, but vastly different cost. TypeSafe was way cheaper, and did beat Qwen on performance. Closest we can get using LLMs I think. Source:
I gave 2 local AI models 4 browser tabs and 4 jobs at the same time 🧠
Gemma 4 vs Qwen 3.8, all local on my M5 MacBook, 128GB Both went 16/16. Gemma ~30% faster Twist: 4 tabs at once barely helped. The brain takes turns. Fixing that next Who gets the rematch?
Here is the video of qwen 3.8 flash next autonomously building a visually striking website, start to finish, 29 minutes at 9.7x speed.
The stack: official fp8 on 2x dgx spark, tensor parallel over one cable, 256k context loaded, 45 tok/s sustained with mtp on, hermes agent
YuE2 is a new AI model for music generation, running 100% locally.
I used Qwen 3.8, equally local LLM to create the lyrics, I had YuE2 create a romantic ballad with a couple. It took about 4 minutes.
You have reached the end of the archive
All of qwen38