FRAMEWIREIndonesiaUpdated Aug 23Live wire
0:00 / 0:00

UNREAL. Qwen 3.8 27B is now happily running on an RTX 4060 locally with only 8GB of VRAM.

You’re looking at a 64k context window thanks to Unsloth’s fresh IQ4_XS quant, and it’s just 14.6GB on disk. Prefill is around 150 tok/s, decode sits at ~5 tok/s using native MTP. Only

CyrilXBTAug 2384
0:00 / 0:00

Qwen 3.8 model on your iPhone 🔥

Someone successfully ran the Qwen 3.8 27B model locally on a MacBook Pro 💻 • Full remote control via iPhone 📱 • Connection and control are done easily through clonkapp 🚀

ثامر الغاليAug 2212
0:00 / 0:00

How i run the local QWEN 3.8 27B via an iPhone

The power we have is insane. thanks to china <3

Paulius 🏴‍☠️Aug 22126
0:00 / 0:00

Four models. Three tasks.

ZERO FIXES. everything looked the same at the start. but after one prompt, the difference became obvious. GPT-5.6, Claude Opus 5, Qwen 3.8 Max and Grok 4.6 had to build a premium product page, a playable browser game, and an animated rainy city scene

BruckyAug 2214