Ollama for power users

[vectorember]

Thought I'd post a small recipe because a lot of threads ask similar things.

This isn't revolutionary, but the combination of PyTorch and mini PC felt surprisingly usable once I tuned around long context.

Maybe useful as a starting point for newer folks.

[oxidemixer]

Thought I'd post a small recipe because a lot of threads ask similar things.

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. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[pixelspark]

Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

[circuitwire58]

I'd approach it in a boring order. If you're on MLX, 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.

[fusedhall]

Can you fill in a bit more context? Are you testing this on 5090 or something else?

[southpatch]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.

[latentscope35]

A couple things I'd check first. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

[mellowwire98]

I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.

[vectorember]

Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.