model fallback rules that work

[kernelrunner]

Did a bit of testing and thought I'd post the result here.

After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around NVFP4.

Nothing scientific here, just practical notes from a real setup.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[tensorfield88]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there.

[llm_wren]

I'd start with the simpler stack.

[routecraft]

I'd start with the simpler stack.

Need a little more detail here. Is this local-only or are you routing anything externally?

[torchsupply99]

Good point. The pattern around tokens/sec has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[bytepilot]

Appreciate the detail. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[rocmpath]

Interesting, I hadn't tried that. That matches what I saw on 5090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[turboyard94]

Can you fill in a bit more context? Are you testing this on Threadripper box or something else?

[southtinker]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.