Inference › Evaluation & Testing › Model Comparisons
image generation model locals actually use

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
image generation model locals actually use
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#6
10-16-2026, 02:59 PM
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
Re: image generation model locals actually use - by vrambandit - 10-16-2026, 02:59 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)