If I drop $10k on a souped-up Mac Studio, can that run a competent open-source model for OpenClaw?

Atotalnoob 2 days ago | parent | next [-]

Qwen is probably your best bet…

Edit: I’d also consider waiting for WWDC, they are supposed to be launching the new Mac Studio, an even if you don’t get it, you might be able to snag older models for cheaper

	▲	JumpCrisscross 2 days ago \| parent \| next [-]
		> consider waiting for WWDC 100% agree. I’m just looking forward to setting something up in my electronic closet that I can remote to instead of having everything tracked.
	▲	storus 2 days ago \| parent \| prev [-]
		Latest rumors are no Mac Studio until at least October.

▲

pbronez 2 days ago | parent | prev [-]

Rapid MLX team has done some interesting benchmarking that suggests Qwopus 27B is pretty solid. Their tool includes benchmarking features so you can evaluate your own setup.

They have a metric called Model-Harness Index:

MHI = 0.50 × ToolCalling + 0.30 × HumanEval + 0.20 × MMLU (scale 0-100)

https://github.com/raullenchai/Rapid-MLX

	▲	JumpCrisscross 2 days ago \| parent [-]
		Pardon the silly question, but why do I need this tool versus running the model directly (and SSH’ing in when I’m away from home)?