FRAMEWIREIndonesiaUpdated Sep 12Live wire
0:00 / 0:00

1200+ t/s on cerebras Qwen 3.8 27b ..

I need more of this in my life!!

Base Camp BernieSep 123
0:00 / 0:00

Basic circuit design with my FLAI harness and using qwen 3.8 flash via open router

Filip KarandySep 12
0:00 / 0:00

Qwen 3.8 27b NVFP4 + 5090 + Podman + Ninfer + arch hitting 443 tok/s decode @ c4

Oh. my. god.

JayceSep 12
0:00 / 0:00

What can the AMD Strix Halo mini PC do?

It is meant to run AI models locally. That is, on your table, in the company, not on someone else's servers. Work on your data without sending it to anyone and doesn't stop when a subscription expires. I turned us around

Mauro ChiarugiSep 11