+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Model Comparisons (https://www.datasculpting.ai/inference/forumdisplay.php?fid=67)
+--- Thread: VRAM saving for image generation: what are you seeing? (/showthread.php?tid=1388)
Pages:
1
2
VRAM saving for image generation: what are you seeing? - dockember - 10-18-2026
Maybe I'm missing something obvious.
I'm mostly working with FLUX in SGLang on A6000. The part I'm trying to understand is KV cache pressure.
If you've tested something similar, what did you keep and what did you stop bothering with? The logs were somehow calmer than I was.
Re: VRAM saving for image generation: what are you seeing? - pixelcrate82 - 10-18-2026
Thanks, that helps. That matches what I saw on M3 Max. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: VRAM saving for image generation: what are you seeing? - deepseeked - 10-18-2026
Interesting, I hadn't tried that. That matches what I saw on Threadripper box.
Re: VRAM saving for image generation: what are you seeing? - ggufwire22 - 10-18-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: VRAM saving for image generation: what are you seeing? - amberplane - 10-18-2026
Ran a quick check on my box. On 7900 XTX with Ollama, I saw basically the same behavior.
Re: VRAM saving for image generation: what are you seeing? - signaltrack44 - 10-18-2026
Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there.
following this because I'm in the same boat.
Re: VRAM saving for image generation: what are you seeing? - emberquill - 10-18-2026
Good point. That matches what I saw on A6000.
Re: VRAM saving for image generation: what are you seeing? - amberkite - 10-18-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
Re: VRAM saving for image generation: what are you seeing? - ggufwire22 - 10-18-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: VRAM saving for image generation: what are you seeing? - nanogarden - 10-18-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there.