# What is Muse Spark Open, and can you really run it at home on two Mac Studios? Date: 2026-10-16 · Author: Robert Scales · https://guidetoartificialintelligence.com/en/learn/muse-spark-open-weights-licence-mac-studio/ **Answer:** Muse Spark Open is the downloadable version of Meta's Muse Spark, released on October 15, 2026, with 816 billion parameters, 42 billion active per token. Meta shows it running on two Apple M5 Ultra Mac Studios with 512 GB each, and its card asks for 700 GB of graphics memory otherwise; a custom licence adds attribution and other conditions. Yesterday, Meta released the weights of Muse Spark Open, the downloadable version of its Muse Spark line. **Weights** are the learned numbers that make up a model. Meta ranks it first among open-weight models from the United States. That is Meta's own claim, based on its own benchmark table, and a fuller evaluation report is still to come. The headline that will catch many readers is that it runs "at home". That is accurate for a particular sort of home, one with two top-end Mac Studios on the desk. ## What was released Muse Spark Open shares its base model with Muse Spark 1.3, according to the PyTorch team, and has had extra safety post-training because an open copy runs without the guardrails Meta applies on its own service. | Item | Muse Spark Open | |---|---| | Total parameters | 816 billion | | Active parameters per token | 42 billion | | Context window | 1 million tokens | | Inputs | Text, images, audio and documents | | Files | BF16 and NVFP4 versions; about 1,644 GB in the main repository | | Access | Hugging Face form, reviewed manually | | Licence | Muse Model License | Meta's model is a **mixture of experts**, in which only some parameters do the work for each token (a small piece of text). So 42 billion sets the compute per token, and 816 billion sets the memory needed. Note the gate as well: you must fill in a form and be approved, unlike ungated repositories that download straight away. You can also get it through the Amazon, Google Cloud and Microsoft model catalogues, and hosts such as Together AI, OpenRouter, Groq and Fireworks AI serve it. ## What the hardware claim means Meta's model card asks for at least 700 GB of graphics memory for the NVFP4 version and 2 TB for the full-precision BF16 one. **NVFP4** is a compact 4-bit format and **BF16** a 16-bit format, so these are two points on the size-and-quality trade-off. Meta's desktop route uses Apple's unified memory, where the processor and graphics share one pool. Each M5 Ultra Mac Studio can give its graphics up to 512 GB, so two machines hold about a terabyte between them. Meta says the chip's memory bandwidth, 1.2 TB per second, is enough to read the small slice of the model each token needs. Here's a comparison: | Route | Memory | What it suits | |---|---|---| | Two Mac Studios, M5 Ultra, 512 GB each | About 1 TB in total | One person or small team, private work, with the MLX framework | | Data-centre GPUs, 80 GB each, NVFP4 | 700 GB means about nine cards | Several users at once, through SGLang or vLLM | | Hosted API | None | Trying it, most production use | Meta's demonstrations include fixing bugs in an open-source iOS app and driving video-editing software with the model reviewing footage. Those are the company's own examples, so test the responsiveness yourself before you buy anything. > **Try it:** Before spending anything, run 20 real tasks through a hosted endpoint such as OpenRouter or Together AI. If the results don't beat your present tools, the hardware question goes away. ## How Meta tuned it for builders The PyTorch team published details alongside Meta's post. Muse Spark Open ships with kernels, the small routines doing the heavy maths on the chip, written in Helion, a PyTorch language. They report kernel speedups between 1.03 and 3.95 times on NVIDIA and AMD chips, but only a 3 percent improvement overall on AMD's MI350, so the end-to-end gain is much smaller than the top figure suggests. For tuning, TorchTitan, a PyTorch training platform, adds support for supervised fine-tuning, LoRA adapters (small add-on layers that adjust a model) and reinforcement learning. Meta's card also says the model is not intended for people under 18, and it recommends human confirmation before irreversible actions when the model operates tools. That advice applies to anyone giving an agent real permissions. ## What does the Muse Model License require from you? The licence is free and starts with broad permission, including fine-tuning and distillation. It is not Apache 2.0, unlike Meta's smaller Muse Glimmer. The conditions that matter: | Condition | Who it touches | |---|---| | Display "Built with Muse Spark Open" in the interface, documentation, site or settings | Every product using the model or a derivative | | Notify Meta and sign a separate agreement before offering it as a service | Businesses selling model access via API whose group revenue tops $20 million US over 12 months; internal use, research and features of your own product are exempt | | Follow the Usage Policy, which is part of the licence | Everyone | "Derivatives" is the term to watch. It reaches any AI model built, trained, tuned or distilled with the help of the software **or its outputs**. So if you use Muse Spark Open's answers to train a small model of your own, that small model comes under the attribution rule too. The Usage Policy bans things such as creating malware and the unlicensed practice of professions like law or medicine, and the card separately warns against breaking trade-compliance laws. For a Canadian company, none of this requires special steps beyond ordinary legal care, but a firm in a regulated field should read the policy against its actual use. Keep a dated copy of the licence with your project, since your rights rest on the version you accepted. ## Sources - Introducing Muse Spark Open: https://research.meta.ai/blog/muse-spark-open - meta-models/Muse-Spark-Open-816B-A42B: https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B - Muse Spark Is Now an Open-Weights Model: https://pytorch.org/blog/muse-spark-open/ --- From the Guide to Artificial Intelligence, by Robert Scales, published by Holistic Hybrid Inc. Share and adapt it under CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/): credit the guide, link to https://guidetoartificialintelligence.com/en/learn/muse-spark-open-weights-licence-mac-studio/, no commercial use without permission, and keep the same licence.