Ox Alpha's version. For me so far with websites/shaders/generative on output alone it hasn't dethroned Qwen 3.8 27b.
Ox Alpha website tests, I'll let you all be the judge.
Same prompts used for Qwen 3.8 27b More videos incoming!
To go from Qwen 3.8 to GLM 5.3 flash.
Qwen 3.8 27B on hit 3.3x faster decode in 7 days.
Here's what happened and what we're thinking next. Result (so far) Median decode speed increased from 26 tok/s to 87.9 tok/s on the verifier M5 Max (33 to 93.1 tok/s across the eight prompts), with
You have reached the end of the archive
All of qwen38