They've done considerable effort in making sure this model can run on basically every model runner, from Unsloth to MLX, https://dev.meta.ai/docs/muse-spark-open/deploy

▲

alberth 3 hours ago | parent | next [-]

As someone not in the loop, can you explain more of what you mean.

▲

mixtureoftakes 3 hours ago | parent | next [-]

day one support for all inference engines so that whichever kind of capable computer you have, you can run it. you do need a really capable computer though

▲

mcphage 3 hours ago | parent [-]

> you do need a really capable computer though

They suggest a pair of Mac Studios w/ M5 Ultra chips and 512 GB of RAM. A single Mac Studio w/ M5 Ultra and half that RAM (256 GB) is around $11k, and the 512 GB option isn't even available yet. So.... yeah.

▲

trvz 3 hours ago | parent [-]

You can just use your old dual 512GB M3 Ultras until you get the M5s. Man, people always whine about something...

	▲	KerrAvon 2 hours ago \| parent \| next [-]
		This comment has the unusual property of being applicable whether or not it's sarcasm!
	▲	mcphage 2 hours ago \| parent \| prev [-]
		O shit, I didn't even think of that. I've got a few of those kicking around, honestly I was just using them as doorstops at this point.

▲

armcat 3 hours ago | parent | prev [-]

[flagged]

▲

nico 3 hours ago | parent | prev | next [-]

Anyone who has tried a smaller/quantized version locally on apple silicon? Would love to know your experience, also tk/s on what hardware specs?

▲

twitexplore 3 hours ago | parent | prev [-]

Yes, but still, what about users looking for NPU support. What happened to Microsoft's copilot+ PC campaign? (the NPU hardware, not the logo key and ad campaign) AMD's XDNA2 NPU is best supported by ONNX, I think Qualcomm Hexagon is too. The best consumer unified architectures are Apple, AMD ai+ and Qualcomm Snapdragon X Elite, even intel has an NPU offering.

▲

d2kx 3 hours ago | parent | next [-]

NPUs are meant for tiny, tiny models that can run basically at all times but cannot affect battery life (e.g. translation, live-video cleanup, filesearch etc.), not for big LLMs. This is about 500 times to large for a NPU.

▲

fg137 15 minutes ago | parent | prev | next [-]

Copilot+ PC is such a terrible and wasteful marketing effort that Microsoft has given it up.

NPUs are not inherently useless, but definitely so the way they are forced onto users machines.

▲

BlackRabbit1 3 hours ago | parent | prev | next [-]

NPUs you can find in AMD high-end CPUs are closer to specialized DSPs (basically big VLIW/SIMD vector units).

People love doing heavy math stuff with them (https://destevez.net/2026/05/getting-peak-tops-on-a-ryzen-ai... - not my blog)

▲

HarHarVeryFunny 2 hours ago | parent | prev [-]

There are plenty of smaller less powerful open weights models if all you have to run it on is an NPU.

This is a much larger more powerful model, so running it locally will not be for everyone, but you can still run it via a hosting service such as Fireworks AI.

▲

twitexplore 39 minutes ago | parent [-]

I was mistaken in my thinking that open models are able to be quantized to run on average consumer hardware, I think they have outgrown that concept.

	▲	HarHarVeryFunny 6 minutes ago \| parent [-]
		I guess that's the attraction - that they may be small enough (likely quantized) so that you can run them locally, so there is no privacy issues, and no-one can turn it off, etc, but technically "open weights" is just referring to models, of any size, where they give you the weights (basically give you the model) so you can run it yourself, instead of having to access it via paid API running on some computer that they control.