09-18-2026, 11:03 AM
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
measure twice, benchmark three times
|
draft model choices for Phi
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
draft model choices for Phi - by cacheline - 09-09-2026, 03:21 AM
Re: draft model choices for Phi - by fastfield4 - 09-11-2026, 03:49 AM
Re: draft model choices for Phi - by vramarch - 09-11-2026, 04:47 AM
Re: draft model choices for Phi - by cacheline - 09-11-2026, 04:22 AM
Re: draft model choices for Phi - by cacheline - 09-12-2026, 05:23 AM
Re: draft model choices for Phi - by cobaltworks25 - 09-12-2026, 05:45 AM
Re: draft model choices for Phi - by cacheline - 09-12-2026, 07:10 AM
Re: draft model choices for Phi - by promptpoint - 09-15-2026, 07:50 AM
Re: draft model choices for Phi - by amberrunner - 09-15-2026, 08:24 AM
Re: draft model choices for Phi - by cacheline - 09-18-2026, 08:45 AM
Re: draft model choices for Phi - by visionforge - 09-18-2026, 09:25 AM
Re: draft model choices for Phi - by cacheline - 09-18-2026, 11:03 AM
Re: draft model choices for Phi - by amberrunner - 09-18-2026, 03:30 PM
|
Users browsing this thread: 1 Guest(s)