deepseek-v4.1POST
User switches back from GLM 5.3 to V4.1 Flash for speed and two-Spark fit
After favoring GLM 5.3 Flash for being smarter but slower, the author returns to DeepSeek V4.1 Flash, calling it faster and even smarter than GLM 5.3 while needing only two Sparks.
Javier • priv/acc
@jvr0xArchived 11 days agoOriginally posted 2026.10.20
Javier • priv/acc @jvr0xOriginally posted 2026.10.20
I always liked DeepSeek models, they are smart and fast! When GLM 5.3 Flash got released In started using it more often cuz it was smarter, but slower. I was ok with that sacrifice. Then I got my third spark and thought to run GLM 5.3 Full. Got the weights and all. And now I am going back to DeepSeek V4.1 Flash as it is faster and even smarter than GLM 5.3, and only requires two sparks! 🤩 What a time to be alive
This post quotes another post: x.com/artificialanlys/status/2112218661432000694
x.com/jvr0x/status/2112271408868823291Archived 2026.10.20 12:04