|
image generation model locals actually use
|
10-13-2026, 02:06 PM
Quote:Good point. That matches what I saw on mini PC. The biggest change for me was simplifying the stack instead of adding one more optimization layer. I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. |
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
image generation model locals actually use - by cudapeak - 10-10-2026, 12:01 PM
Re: image generation model locals actually use - by benchplease - 10-10-2026, 12:26 PM
Re: image generation model locals actually use - by fastlab - 10-13-2026, 01:10 PM
Re: image generation model locals actually use - by sparrowhall - 10-13-2026, 02:06 PM
Re: image generation model locals actually use - by vramstream - 10-16-2026, 02:27 PM
Re: image generation model locals actually use - by vrambandit - 10-16-2026, 02:59 PM
Re: image generation model locals actually use - by plainscope50 - 10-16-2026, 03:36 PM
Re: image generation model locals actually use - by southtinker - 10-17-2026, 03:45 PM
Re: image generation model locals actually use - by sparrowcraft - 10-18-2026, 12:07 AM
|
