which local open model do you keep coming back to with LM Studio

[batchshed]

Spent some time on this today and wanted to compare notes.

I've gone back and forth between LM Studio and MLX for Qwen. The interesting difference for me has been workstation thermals.

Interested in tradeoffs more than fan loyalty.

[thetashed24]

Spent some time on this today and wanted to compare notes.

Can you fill in a bit more context? What model, what runtime, and roughly what context size?

[audiodesk]

Spent some time on this today and wanted to compare notes.

Can you fill in a bit more context? Are you testing this on GB200 or something else?

[deepseeked]

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

[mlxgarden]

Interesting, I hadn't tried that. I don't think your conclusion is far off.

[northgrid33]

I hit almost the same issue last night.