FRAMEWIREIndonesiaUpdated Aug 29Live wire
0:00 / 0:00

Qwen 3.8 27b on the agent mode harness.

Built itself a python app to generate the single html. Prompt in the first comment proves the harness value 🏆👇⬇️ ..also impressive workspace structure in agent mode 👏

Nic Wienandt - mtecnicAug 29
0:00 / 0:00

ABSURD. Qwen 3.8 27B is cruising locally on an RTX 4060 with just 8GB of VRAM.

That’s a 64k context window courtesy of Unsloth’s brand-new IQ4_XS quant, and the whole thing weighs in at 14.6GB on disk. Prefill lands around 150 tok/s; decode hovers at ~5 tok/s with native MTP.

CyrilXBTAug 29116
0:00 / 0:00

Japanese Tea Garden Bench - Qwen 3.8 Flash Next

Just lucky, I guess. This one took 6 hours and several million tokens, at medium effort. I would say good job, but the z-fighting is prominent, and it might never have finished had I not stopped it.

Mooncast ProductionsAug 292
0:00 / 0:00

This is my personal experience with Qwen 3.8 27B in Hermes versus Grok 4.6 in Grok Build.

AgentSparko 💥Aug 2914