personal-testing

Tag

Cards List
#personal-testing

@AstroHanRay: If you need to use GLM-5.2, based on personal testing, Ollama Cloud Pro is the best choice on the market. Plenty of capacity for your money—$20 is basically more than enough unless you have heavy concurrent usage. Its overseas plan at http://Z.ai at the same price can't compete in value, and there's also...

X AI KOLs Timeline ↗ · 2026-07-02 Cached

Recommends using the Ollama Cloud Pro service to run the GLM-5.2 model, considers the $20 plan better value than Z.ai's overseas plan at the same price, and notes that the afternoon period has triple consumption affecting efficiency.

0 favorites 0 likes
#personal-testing

@jiayuan_jy: A few objective clarifications: 1) This post has nothing to do with MiniMax (I never take sponsored posts). 2) 'Subjective feel' is not the same as actual performance; it's not quantitative data. After more extensive experience, overall coding ability is a qualitative improvement compared to m2.7. A current shortcoming is that 1-shot results compared with...

X AI KOLs Following ↗ · 2026-06-01 Cached

Jiayuan Zhang shared his initial experience with the M3 model's coding ability, stating that it is a qualitative improvement compared to m2.7, but the 1-shot results are not as comprehensive as Opus 4.6/4.7 and GPT5.5.

0 favorites 0 likes
← Back to home

Submit Feedback