Inference › Evaluation & Testing › Benchmarks v
eval setup for local models

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
eval setup for local models
mangowire Offline
Junior Member
**
Posts: 29
Threads: 6
Joined: Sep 2026
Reputation: 0
#8
09-14-2026, 02:28 PM
Quote:Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up bef

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there.
still benchmarking everything
Find
Reply


Messages In This Thread
eval setup for local models - by circuitworks90 - 09-11-2026, 03:09 PM
Re: eval setup for local models - by nanobrook - 09-12-2026, 12:29 AM
Re: eval setup for local models - by benchplease - 09-13-2026, 01:47 PM
Re: eval setup for local models - by kernelarch - 09-12-2026, 12:56 AM
Re: eval setup for local models - by northgrid33 - 09-13-2026, 01:38 PM
Re: eval setup for local models - by quiethouse - 09-14-2026, 02:04 AM
Re: eval setup for local models - by mangowire - 09-14-2026, 02:28 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)