Apple ML Research: Muse Spark Open with MLX on Mac Studio

FWIW, single M5 Ultra with 256GiB runs DeepSeek 4.1 Flash 0910 just fine (~3200 tok/s prefill, ~45 tok/s). M5 Max w/ 128GiB runs GLM 5.3 Flash also fine.

I also benchmarked both on quality benchmarks (MathArena Apex / GPQA Diamond etc) to make sure the quality is what you get from the official numbers.

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.

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.

Not exactly your average "desk", but still neat.

  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.

It's a good article which showcases direction of travel, i am sure mac studio will get more and more powerful in coming generations but for now it's way to expensive for local setup.

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.

A 800B model that performs way worse than other 300B ones. Well...

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.

Preparing to upsell those very expensive Macs coming later this month, are we.

I -- love -- an article -- full of -- em -- dashes.