FRAMEWIREIndonesiaUpdated Aug 29Live wire
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 2937
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 295
0:00 / 0:00

I made the subtitles semi-transparent so it should be easier to see.

I made the subtitles semi-transparent so it should be easier to see. Completion Beatles style composition with Vox Score → Cover with Suno → Import into LaViale → Analyze with Whisper → Direct with Qwen 3.8 → Krea 2 +… I made the subtitles semi-transparent so it should be easier to see.

Koya MatsuoAug 295