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
Ox Alpha is definitely NOT GLM 5.5, it’s honestly way worse than GLM 5.3
Qwen 3.8 27B choked. Opus 5 still claps everything easily
Qwen 3.8 2.4T built a Call of Duty clone in one prompt 🪖
You have reached the end of the archive
All of qwen38