FRAMEWIREIndonesiaUpdated Aug 27Live wire
0:00 / 0:00

Build a beach simulator using Qwen 3.8 and GLM-5.3 Flash

Qwen 3.8 used about 2M tokens and was free because I ran it locally GLM-5.3 Flash used about 2-3M tokens and was free on OpenCode

KaranAug 276
0:00 / 0:00

Qwen 3.8 Max reportedly coded alone for 16 straight days with no human intervention.

Alibaba gave the 2.4-trillion parameter AI a single instruction, a blank folder and left it to write, test, debug and refine its own code until it produced working software. Pajeet jobs killer!!

Vanta LogikAug 27
0:00 / 0:00

Qwen 3.8 Flash Next (125B A6B MoE) Vs Qwen 3.8 27B (dense)

Fede(URU) 🇺🇾Aug 27
0:00 / 0:00

Holy shit that is some of the best Pagoda I've seen generated locally and that's by a 4-bit quant on a…

Holy shit that is some of the best Pagoda I've seen generated locally and that's by a 4-bit quant on a single 3090 (Qwen 3.8 Flash Next) - input + output 54k tokens. One shot:

VieirowskiAug 277