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.
This is my personal experience with Qwen 3.8 27B in Hermes versus Grok 4.6 in Grok Build.
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.
Qwen 3.8 27B thinking effort comparison, personally I feel the medium and thinking off not worth it, either go with thinking low or xhigh..
Note: quant may impact the model perf, looks like 4bit quant is way easier to get itself in thinking loop
You have reached the end of the archive
All of qwen38