logoalt Hacker News

mmastractoday at 4:17 PM4 repliesview on HN

I previously posted that DS4Flash was _good_ but not _great_ on two DGX Sparks, but I have to say that GLM-5.3 is pretty amazing. It's been able to tackle all the random hard problems I've thrown at it and it has the intuition that DS4Flash seems to lack.

We're nowhere near a Fable-class model IMO, but things are going to get interesting in this next year.


Replies

VariousProgramstoday at 8:22 PM

It's early days, but GLM 5.3 Flash is the first local model that feels good enough to me to be a "main" model without debating whether each problem needs to be sent to a stronger model. DS4 Flash is good enough at implementing given a plan, but I wasn't always a fan of what it came up with when asked to plan something.

The good news is it can only get better from here.

petutoday at 6:21 PM

I assume that's about 5.3 Flash, not full?

show 1 reply
villishtoday at 4:46 PM

What quant are you running and tps?

show 1 reply
deagle50today at 6:24 PM

do you mean GLM 5.3 flash?