+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Quality / Reliability Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=68)
+--- Thread: local video generation really usable yet for Mistral (/showthread.php?tid=1481)
Re: local video generation really usable yet for Mistral - paperrunner - 10-18-2026
that fixed it for me too. At this point the real bottleneck is my patience.
Re: local video generation really usable yet for Mistral - kernelghost - 10-18-2026
I'd start with the simpler stack.
Re: local video generation really usable yet for Mistral - turboscope - 10-18-2026
Quote:Posting this in case it saves someone else a little time.
My first guess would be this: On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: local video generation really usable yet for Mistral - llm_wren - 10-18-2026
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
local video generation really usable yet for Mistral - sparrowcraft - 10-19-2026
Posting this in case it saves someone else a little time.
I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about prefix caching.
Would rather learn from your scars than collect my own all at once.
Re: local video generation really usable yet for Mistral - vrampilot - 10-19-2026
Thanks, that helps. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: local video generation really usable yet for Mistral - visionforge - 10-19-2026
Good point. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.