best mini PC for local use with TensorRT-LLM

[quantsupply]

This keeps coming up in conversation so I figured I'd start a thread.

One thing I keep noticing is that people underestimate prefix caching until they actually try to run this stuff for more than one afternoon.

Wondering if this is just where the whole space is heading now.

[latentscope35]

This keeps coming up in conversation so I figured I'd start a thread.

Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[homelabhenry]

A couple things I'd check first. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[promptfield]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.

[homelabhenry]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals. Not glamorous advice, but repeatable baselines save a lot of time.

[byteyard]

That matches what I was seeing. I don't think your conclusion is far off.

[homelabhenry]

That matches what I was seeing. I ended up in about the same place using PyTorch. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.