Comment by mmastrac
15 hours ago
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.
> We're nowhere near a Fable-class model IMO, but things are going to get interesting in this next year.
I'm wondering of you could clarify your thoughts on this. I've had a hard time evaluating what Fable-class actually is capable of that sets them (or really it) apart from other models in a very significant way.
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.
What coding harness are you using? I am trying to take the plunge and wondering which I should use
I assume that's about 5.3 Flash, not full?
Yes, sorry 5.3 flash.
What quant are you running and tps?
NVFP4 ~20-30tps (MTP + vision, no dflash2).
do you mean GLM 5.3 flash?