CLI helpers for local models with MLX

[batchshed]

Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

Would rather learn from your scars than collect my own all at once.

[rocmhouse90]

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

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[mlxgarden]

Appreciate the detail. I ended up in about the same place using llama.cpp.

[rocmpath]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[cachebench]

Thanks, that helps. That matches what I saw on dual 3090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[mlxgarden]

I think the bottleneck is somewhere else. I've seen people blame tokens/sec when the real issue was much more mundane.

[relayforge]

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