So, Meta will spend millions/billions on building open-weight models and then people will send Apple $20,000 to run them. Seems like a good deal for Apple.
They have the best strategy of bigtechco: let others figure out the squishier layers while they focus on selling the best hardware. Privacy has incredible value to a lot of individuals and industries. $20-80k in hardware that *appreciates* the moment you buy it is a reasonable investment for a lot of SMBs, and still less than a single Nvidia rig. Privacy pays.
While right now Mac Studio is not a budget device and it certainly costs more than the subsidised subscription, the promise that one day we can run these models on commodity hardware is exciting.
In this post, we show how to run the latest frontier-class model — Muse Spark Open, with nearly a trillion parameters — right from your desk, using the latest version of MLX, released today. On a cluster of four Mac Studios, Muse Spark Open generates over 36 tokens per second (see Figure 1), well above average human reading speed. Beginning on a single Mac Studio (up to 512GB of unified memory), then scaling out across multiple Macs with the RDMA over Thunderbolt driver, below we share an overview of the range of models you can now run on Mac Studio.
Yes, I'm very glad they're doing this, but as of 2026, it's a bit academic. Pricing for the 512GB Mac Studio hasn't even been announced yet, but the 256GB version starts at $9499. So when you start talking about four of those puppies, it's substantial.
Someone else will do the math on how many years it would take to spend $40k on Muse Spark Open via OpenRouter.
It seems Apple figured they could sell more Mac Studios on the basis of frontier local AI models, profit to be made while users haven't figured out the math yet.
Don't get me wrong; in the long term I see the price of local inference falling as their chips continue to get 15-20% faster every year, and meanwhile the "intelligence per billion parameter" chart is rising. There will be a magic point where they cross, and "good enough" reaches your phone. That's when Apple starts to drink Nvidia's milkshake.
It was only like $14k new. Why are you people acting like nobody has this stuff? People were already building clusters when that thing first came out. The research isn't bunk just because the refresh hasn't landed yet, my god.
I think they're sandbagging Qwen pretty heavily by benchmarking Meta's model at 4-bit, against Qwen only at native BF16 (and nothing else shown). That's not a quant most users would choose.
I get that this is cross-brand marketing for Apple's partner, Meta; but really Muse Spark isn't even in the top *ten* models I'd consider if I had a 512 GB M5 in my paws. Or a cluster of them.
I find it bizarre of Apple to do anything publicly in partnership with Meta. I always thought the reasons Apple snubbed Facebook were out of values and principles not business. That could be wrong. Now that Meta has a line of business that Apple can finally charge a platform tax on there is new reason to start sleeping with them.
So, Meta will spend millions/billions on building open-weight models and then people will send Apple $20,000 to run them. Seems like a good deal for Apple.
How many 5080 16 Gig cards would you have to buy to run the same model, and what would that cost?
Exactly why does Apple need to do any model training/development? They are out here selling the shovels.
They have the best strategy of bigtechco: let others figure out the squishier layers while they focus on selling the best hardware. Privacy has incredible value to a lot of individuals and industries. $20-80k in hardware that *appreciates* the moment you buy it is a reasonable investment for a lot of SMBs, and still less than a single Nvidia rig. Privacy pays.
I am super excited about this.
While right now Mac Studio is not a budget device and it certainly costs more than the subsidised subscription, the promise that one day we can run these models on commodity hardware is exciting.
Not exactly your average "desk", but still neat.
Yes, I'm very glad they're doing this, but as of 2026, it's a bit academic. Pricing for the 512GB Mac Studio hasn't even been announced yet, but the 256GB version starts at $9499. So when you start talking about four of those puppies, it's substantial.
Someone else will do the math on how many years it would take to spend $40k on Muse Spark Open via OpenRouter.
It seems Apple figured they could sell more Mac Studios on the basis of frontier local AI models, profit to be made while users haven't figured out the math yet.
Don't get me wrong; in the long term I see the price of local inference falling as their chips continue to get 15-20% faster every year, and meanwhile the "intelligence per billion parameter" chart is rising. There will be a magic point where they cross, and "good enough" reaches your phone. That's when Apple starts to drink Nvidia's milkshake.
Apple and NVIDIA prices are not going to fall.
Their competitors will. Anyone locked into these two ecosystems are willingly going along with it.
There was the M3 Ultra 512GB Mac Studio, though.
…which is in the region of €20k on eBay, so the calculus doesn’t really shift…
It was only like $14k new. Why are you people acting like nobody has this stuff? People were already building clusters when that thing first came out. The research isn't bunk just because the refresh hasn't landed yet, my god.
I think they're sandbagging Qwen pretty heavily by benchmarking Meta's model at 4-bit, against Qwen only at native BF16 (and nothing else shown). That's not a quant most users would choose.
I get that this is cross-brand marketing for Apple's partner, Meta; but really Muse Spark isn't even in the top *ten* models I'd consider if I had a 512 GB M5 in my paws. Or a cluster of them.
Hilarious how they managed to put out an entire press release about Meta’s technology without mention Meta other than what is in the code references.
It’s not a press release and not about Meta’s technology.
The title (“Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio”) doesn’t even mention Muse.
It’s more like an advertorial for their tech.
Still weird, and against brand, for them to lead with this particular model from that particular company. The groans are still earned.
I find it bizarre of Apple to do anything publicly in partnership with Meta. I always thought the reasons Apple snubbed Facebook were out of values and principles not business. That could be wrong. Now that Meta has a line of business that Apple can finally charge a platform tax on there is new reason to start sleeping with them.
Its still weird though.
The datacenters are not full of Mac studios but Nvidia hardware.
They are known for macbooks.
And they are not willing to build proper apple servers for all the build systems people have.
They did, and few people bought them, so they stopped.
They don’t lead with it. The title of the actual article is “Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio”.
The submitter changed it to “Apple ML Research: Muse Spark Open with MLX on Mac Studio”
Second paragraph: "In this post, we show how to run the latest frontier-class model — Muse Spark Open, with nearly a trillion parameters..."
Preparing to upsell those very expensive Macs coming later this month, are we.
I -- love -- an article -- full of -- em -- dashes.