comparing models without fooling yourself on GB200

Thread Rating:

0 Vote(s) - 0 Average
1
2
3
4
5

Linear Mode

comparing models without fooling yourself on GB200

northgrid33 Offline

Offline

Member

Posts: 52
Threads: 6
Joined: Sep 2026
Reputation: 0

#14

10-19-2026, 05:29 AM

Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

comparing models without fooling yourself on GB200 - by griffinloom66 - 10-18-2026, 11:09 PM

Re: comparing models without fooling yourself on GB200 - by deltastation - 10-18-2026, 09:21 PM

Re: comparing models without fooling yourself on GB200 - by llmtrack26 - 10-19-2026, 12:13 AM

Re: comparing models without fooling yourself on GB200 - by kernelghost - 10-19-2026, 12:46 AM

Re: comparing models without fooling yourself on GB200 - by plainember52 - 10-19-2026, 01:04 AM

Re: comparing models without fooling yourself on GB200 - by vramridge - 10-19-2026, 01:16 AM

Re: comparing models without fooling yourself on GB200 - by circuitworks90 - 10-19-2026, 02:10 AM

Re: comparing models without fooling yourself on GB200 - by quiethouse - 10-19-2026, 02:08 AM

Re: comparing models without fooling yourself on GB200 - by batchpeak - 10-19-2026, 03:06 AM

Re: comparing models without fooling yourself on GB200 - by deltastation - 10-19-2026, 03:35 AM

Re: comparing models without fooling yourself on GB200 - by batchfield55 - 10-19-2026, 05:28 AM

Re: comparing models without fooling yourself on GB200 - by kernelarch - 10-19-2026, 04:03 AM

Re: comparing models without fooling yourself on GB200 - by prompttinker44 - 10-19-2026, 04:14 AM

Re: comparing models without fooling yourself on GB200 - by northgrid33 - 10-19-2026, 05:29 AM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)