Can I run Meta Muse Spark Open on an RX 9060 XT 16GB?
Key facts
No: it needs about 472 GB and this card has 16 GB of graphics memory.
It needs about 471.8 GB at standard quality (estimate). Checked . ggml-org Q4_K_S GGUF (official ggml-org repo; not Q4_K_M).
Updated · Meta Muse Spark Open on every card
How much memory it needs
That is about 30.6 times what this card has free.
Get a 1-line alert when a faster quant for Meta Muse Spark Open drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new low-bit GGUF/MLX quant fits 128–256 GB rigs or when multi-GPU & Mac Studio prices drop >10% — weekly, zero spam.
What runs Meta Muse Spark Open instead
Nothing among the 43 graphics cards, PCs and Macs on our list runs it fully.
See our picks for Meta Muse Spark Open in Find hardware. Add your budget to see cheaper machines.
For comparison, an RX 9060 XT 16GB costs $522€564, new (cheapest in-stock board on GPU PRIX's German board list). Card details
Meta Muse Spark Open on other graphics cards
Doesn't fit10
Not enough graphics memory: it needs about 471.8 GB.
- RTX 3060 12GBhas 12 GB
- RTX 4060 Ti 16GBhas 16 GB
- RTX 3090has 24 GB
- RTX 4090has 24 GB
- RTX 5080has 16 GB
- RX 9060 XT 16GBhas 16 GB
- RTX 5090has 32 GB
- RX 7900 XTXhas 24 GB
- Dual RTX 3090has 48 GB
- Dual RTX 4090has 48 GB
More about the model itself, what it is good at and its licence: Meta Muse Spark Open.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Doesn't fit | 470.1 GBmeasured file | 0.9 GB | 0.8 GB | 471.8 GB | 15.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Doesn't fit | 579.4 GB | 0.9 GB | 0.8 GB | 581.1 GB | 15.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Doesn't fit | 873.1 GB | 0.9 GB | 0.8 GB | 874.8 GB | 15.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | 1,632.0 GB | 0.9 GB | 0.8 GB | 1,633.7 GB | 15.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Doesn't fit | 470.1 GBmeasured file | 2.5 GB | 0.8 GB | 473.4 GB | 15.4 GB |
speed: not estimated for MoE yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . ggml-org Q4_K_S GGUF (official ggml-org repo; not Q4_K_M).
MoE, 256 experts, 8 active per token, 1.8B perception encoder plus audio encoder. The card states 816B total / 42B active; Hugging Face metadata lists 822B including the vision and audio encoders. Licence (Muse Model License): products must display "Built with Muse Spark Open". Model-as-a-Service offerings by licensees whose group revenue exceeds US$20M in any 12 months need a separate agreement with Meta. Internal use and powering your own non-MaaS product are exempt. Gated download (accept terms on Hugging Face). Model card: "optimized to run on two Mac Studios with M5 Ultra using MLX". NVFP4 is for Blackwell GPUs only and needs at least 700GB of VRAM per the card. Vision projector (mmproj) is not a fit row: Q8_0 2.18 GB and BF16 4.10 GB, so add +2.2–4.1 GB for image/audio input. HF blog: 2-bit GGUF (304 GB) ran at 18 tokens per second and oQ3e MLX at ~21 tokens per second generation on a Mac Studio M3 Ultra 512GB (vendor/HF-reported, single test, not ours). Ollama offers muse-spark-open:cloud only (no local tag, checked 24 Oct 2026, https://ollama.com/library/muse-spark-open/tags). Supported in mainline llama.cpp (ggml-org GGUFs), vLLM, SGLang, mlx-lm/oMLX. Speed is not estimated: our speed estimate reads every weight for each token and would understate a sparse MoE.
Some downloads of this model (MLX) only run on Apple Silicon Macs, not on a graphics card.
Questions
- Can I run Meta Muse Spark Open on an RX 9060 XT 16GB?
- No: it needs about 472 GB and this card has 16 GB of graphics memory.
- How much memory does Meta Muse Spark Open need?
- About 471.8 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 470.1 GB for the model file (measured), 0.9 GB to hold the conversation and 0.8 GB of working space.
- How fast is Meta Muse Spark Open on an RX 9060 XT 16GB?
- We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate