Qwen 3.8 Flash Next on my single spark.
Try out with Q3_K_XL. The result is pretty good. Page title & intro caption: 五重塔 (gojū-no-tō — "five-storied pagoda") Start veil: 春 · 塔 (haru · tō — "spring · pagoda")
Glad to introduce the newest agentic art experiment in the lab and the first artwork on SuperRare
SYNTH.MEM.01 //-- Fidelity 6 lab grown agentic entities born in a NousResearch Hermes harness. No memory, no past. They were asked to dream,
This is hilariously bad.
I used Qwen 3.8 Flash Next running locally on my M5 Max. I also ran it using my coding plan with Alibaba against the native model and it looked better it was still an abject failure. I used this and ran it inside of ZCode. Here
Benchmarked Hy4 Preview vs.
GLM 5.3 Flash vs. GLM 5.3 and Qwen 3.8 Flash. Expected Hy4 Preview on WorkBuddy to be impressive, but it completely flopped compared to the rest. GLM 5.3 Flash and Qwen 3.8 Flash run circles around it without breaking a sweat.
You have reached the end of the archive
All of qwen38