Inference › Generative AI › Multimodal
Multimodal discussion

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
Multimodal discussion
visionforge Offline
Member
***
Posts: 121
Threads: 15
Joined: Sep 2026
Reputation: 0
#1
09-22-2026, 03:20 PM
Did a bit of testing and thought I'd post the result here.

After a few runs on 7900 XTX, I ended up with decent performance, but the setup only really made sense once I adjusted around quant drift.

Happy to post more details if anyone wants them.

I care more about stability than squeezing the last possible tokens/sec out of it.
image models by night, local pipelines by day
Find
Reply


Messages In This Thread
Multimodal discussion - by visionforge - 09-22-2026, 03:20 PM
Re: Multimodal discussion - by lablab - 09-24-2026, 03:38 PM
Re: Multimodal discussion - by vramarch - 09-25-2026, 04:18 AM
Re: Multimodal discussion - by macrostack69 - 09-25-2026, 12:38 PM
Re: Multimodal discussion - by macropilot - 09-26-2026, 12:51 PM
Re: Multimodal discussion - by fastquill74 - 09-26-2026, 04:58 PM
Re: Multimodal discussion - by macrostack69 - 09-27-2026, 12:58 AM
Re: Multimodal discussion - by torchshed66 - 09-27-2026, 05:43 AM
Re: Multimodal discussion - by macropilot - 09-27-2026, 10:11 AM
Re: Multimodal discussion - by mangovault67 - 09-27-2026, 11:35 AM
Re: Multimodal discussion - by fastlab - 09-27-2026, 04:06 PM
Re: Multimodal discussion - by sparrowgrid - 09-27-2026, 04:15 PM
Re: Multimodal discussion - by syshouse - 09-28-2026, 12:50 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)