Ox Alpha website tests, I'll let you all be the judge.

Same prompts used for Qwen 3.8 27b More videos incoming!

Loktar 🇺🇸Aug 2123

To go from Qwen 3.8 to GLM 5.3 flash.

Human AI 🇺🇸Aug 21

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

KydoAug 21141

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

Fabiano FirmoAug 213