local video generation really usable yet for Mistral

[paperrunner]

that fixed it for me too. At this point the real bottleneck is my patience.

[kernelghost]

I'd start with the simpler stack.

[turboscope]

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.

[llm_wren]

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.

[sparrowcraft]

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.

[vrampilot]

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.

[visionforge]

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.