Help with Audio / Speech with LM Studio

[modgarden]

I figured I'd ask here before changing everything.

I'm mostly working with Llama in llama.cpp on M3 Max. The part I'm trying to understand is tool calling.

Would appreciate practical advice rather than theory.

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

[mangowire]

Not sure I agree there. I get why that seems right, but on mini PC the bottleneck felt elsewhere.

[sparrowkite53]

Thanks, that helps. I ended up in about the same place using PyTorch.

[signalpeak]

My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[vramridge]

What worked for me was pretty simple. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[cozywire]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4.

[sanescope]

Appreciate the detail. The pattern around HBM constraints 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.

[quietstack]

A couple things I'd check first. On A6000, 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.

[amberkite]

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[sparrowcraft]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?