Muse Glimmer is Meta’s downloadable 30B text-and-image model, distilled from Muse Spark. Ollama lists an 18 GB local variant; the separate MLX tag is about 19 GB. Start with short context on a capable desktop or Mac.
Where it works well
- Text and image input.
- Multi-step reasoning and coding assistance.
- Tool calling in a compatible application.
Common use cases
- Explain an error alongside a screenshot.
- Compare a plan against supplied constraints.
- Suggest a small code change you can review.
Know its limits
- Tools and computer actions require a configured application; the model alone cannot operate your files.
- This is Muse Glimmer, not the much larger Muse Spark Open. The 48 GB estimate is for compressed Glimmer.
- Long conversations, images and speculative decoding need additional memory.
Run it on your computer
Start with a compressed download and a short conversation. Our estimate is about 48 GB of total RAM or Mac unified memory, with room for the operating system. The listed 18 GB download is the model file, not its full running memory use.
Check the model’s supported runtime and hardware before loading it. System RAM on a PC and unified memory on a Mac are different from dedicated NVIDIA VRAM. A memory match doesn’t guarantee compatibility or speed. Choose a smaller model if responses are too slow.
Use a desktop app that supports the listed model format, such as LM Studio or Ollama. Download the exact local variant, load it in Chat, and start with one small task. Model downloads need internet; local chat can work offline once the model is downloaded.
Official model information
Model capabilities checked October 2026. The use cases above are practical starting suggestions, not performance guarantees.