Inference › Optimization & Performance › Quantization v
AWQ vs GPTQ vs GGUF right now

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
AWQ vs GPTQ vs GGUF right now
phasestream53 Offline
Junior Member
**
Posts: 43
Threads: 5
Joined: Sep 2026
Reputation: 0
#1
09-06-2026, 01:24 AM
Did a bit of testing and thought I'd post the result here.

I tried this with FLUX using Ollama on 5090. The headline result was better than I expected, but prefix caching still ended up being the limiting factor.

Happy to post more details if anyone wants them.
Find
Reply


Messages In This Thread
AWQ vs GPTQ vs GGUF right now - by phasestream53 - 09-06-2026, 01:24 AM
Re: AWQ vs GPTQ vs GGUF right now - by northquill - 09-07-2026, 06:06 AM
Re: AWQ vs GPTQ vs GGUF right now - by sanevault - 09-07-2026, 10:14 AM
Re: AWQ vs GPTQ vs GGUF right now - by turboscope - 09-08-2026, 11:02 AM
Re: AWQ vs GPTQ vs GGUF right now - by torchshed - 09-11-2026, 05:25 PM
Re: AWQ vs GPTQ vs GGUF right now - by mangohouse - 09-10-2026, 02:43 AM
Re: AWQ vs GPTQ vs GGUF right now - by quantshed - 09-10-2026, 04:50 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)