10-02-2026, 05:29 AM
What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
|
benchmark result I don't trust: worth it?
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
benchmark result I don't trust: worth it? - by bytelab - 10-01-2026, 01:35 PM
Re: benchmark result I don't trust: worth it? - by orbitgarden - 10-02-2026, 02:18 AM
Re: benchmark result I don't trust: worth it? - by cudascope - 10-02-2026, 04:00 AM
Re: benchmark result I don't trust: worth it? - by batchpeak - 10-02-2026, 04:42 AM
Re: benchmark result I don't trust: worth it? - by mintstream9 - 10-02-2026, 05:29 AM
Re: benchmark result I don't trust: worth it? - by kernelghost - 10-02-2026, 05:48 AM
Re: benchmark result I don't trust: worth it? - by torchkite - 10-03-2026, 06:02 PM
|
Users browsing this thread: 1 Guest(s)