Qwen 3.8 Flash Next on M5 MacBook 24 GB
3-4 tok/s, - reasoning off, - 2k context.
"Fifty Wings in Watercolor" — made using Qwen 3.8 Max
Image references (for geometry and palette via segmentation) supplied by ChatGPT Images 2.5 + watercolor physics simulated with p5.brush (p5.js)
Qwen 3.8 27b Oh, 2000tokens/s, isn’t that just a matter of words?
All generated in real time
I have tracked my macros (mostly protein) for years now.
It is time consuming and extremely annoying. All the apps suck and it take forever. So I gave 3 models the same food photo and asked for the macros: Qwen 3.8 27B on cerebras // 2.46s GPT Astra by OpenAI // 19.55s
You have reached the end of the archive
All of qwen38