FRAMEWIREIndonesiaUpdated Aug 20Live wire
0:00 / 0:00

I requested from qwen 3.8 a simple html game that places on the children's tablet

He sat thinking for about 10 minutes and finally this beauty appeared:

iAug 20
0:00 / 0:00

Qwen 3.8 27B 🚀vs Ornith-1.5-35B

Fede(URU) 🇺🇾Aug 20
0:00 / 0:00

Qwen 3.8 27B now runs locally inside RunAnywhere!

Your app can use the same local AI setup across different hardware. On Mac it runs Swift + mlx. On Windows, Electron + llama.cpp. Different architectures, different inference engines, one SDK call. Your application code doesn’t

RunAnywhere (YC W26)Aug 209
0:00 / 0:00

A 27B model you can run on a single GPU that matches GPT-5.6 Luna?

Artificial Analysis says yes. Our benchmark says… let's talk. Qwen 3.8 27B landed with a real claim behind it: Artificial Analysis scores it 52 on its

Igor KozlovAug 20