comparing models without fooling yourself

Thread Rating:

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

Linear Mode

comparing models without fooling yourself

cacheline Offline

Offline

Senior Member

Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0

#9

10-04-2026, 02:25 AM

Quote:I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.

worth checking the driver first.

measure twice, benchmark three times

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

comparing models without fooling yourself - by sparrowworks88 - 09-30-2026, 11:39 PM

Re: comparing models without fooling yourself - by dockridge - 10-01-2026, 12:24 AM

Re: comparing models without fooling yourself - by marbletrack - 10-02-2026, 01:09 AM

Re: comparing models without fooling yourself - by cacheline - 10-02-2026, 02:51 AM

Re: comparing models without fooling yourself - by batchpeak - 10-02-2026, 03:05 PM

Re: comparing models without fooling yourself - by benchplease - 10-02-2026, 04:15 PM

Re: comparing models without fooling yourself - by kernelghost - 10-03-2026, 05:03 AM

Re: comparing models without fooling yourself - by batchfield55 - 10-03-2026, 05:54 PM

Re: comparing models without fooling yourself - by cacheline - 10-04-2026, 02:25 AM

Re: comparing models without fooling yourself - by batchpeak - 10-04-2026, 04:00 AM

Re: comparing models without fooling yourself - by quiethouse - 10-07-2026, 04:30 AM

Re: comparing models without fooling yourself - by deltastation - 10-07-2026, 05:00 AM

Re: comparing models without fooling yourself - by nanobrook - 10-07-2026, 06:35 AM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)