meta-models · First MLX build 10 Aug 2026 · In Core AI since 19 Aug 2026
Muse-Glimmer-30B
MLXCore AI
TextVision apache-2.0
A 30B parameter vision and text model from meta-models, with 9 MLX builds, from 4-bit to bf16 and Apple Core AI export recipes for macOS.
- Parameters
- 30B From Hugging Face
- Quantisation
- 4-bit Muse-Glimmer-30B-4bit
- Memory needed
- 24 GB Estimate, unified memory
- Download
- 19.4 GB Weights, estimated
- Downloads
- 9.2K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 9 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 30B From Hugging Face
- Compression
- 4-bit Apple’s preset
- Memory needed
- 21 GB Estimate from parameters
- Context
- 128K tokens Fixed at export
- Precision
- FP16 Compute precision
- Platforms
- macOS Mac
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 19 Aug 2026 First registry commit
Memory
Will it fit?Needs about 24 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Muse-Glimmer-30B-4bit --image photo.jpg --prompt "Describe this image"Memory
Will it fit?Needs about 21 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the parameter count at Apple’s compression setting. Apple does not publish package sizes.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run coreai.llm.export muse-glimmer-30b
Apple publishes the recipe, not a ready-made package: these commands convert the original weights to a Core AI .aimodel on your Mac. See the repository for requirements.
MLX builds
9 on mlx-community| Muse-Glimmer-30B-4bit | 4-bit | 19.4 GB | 24 GB | 9.2K |
|---|---|---|---|---|
| Muse-Glimmer-30B-mxfp4 | MXFP4 | 19.4 GB | 24 GB | 891 |
| Muse-Glimmer-30B-nvfp4 | 4-bit | 19.4 GB | 24 GB | 360 |
| Muse-Glimmer-30B-OptiQ-4bit | 4-bit | 19.5 GB | 24 GB | 1.8K |
| Muse-Glimmer-30B-5bit | 5-bit | 22.9 GB | 28 GB | 180 |
| Muse-Glimmer-30B-6bit | 6-bit | 26.4 GB | 32 GB | 385 |
| Muse-Glimmer-30B-8bit | 8-bit | 33.4 GB | 40 GB | 1.7K |
| Muse-Glimmer-30B-mxfp8 | MXFP8 | 33.4 GB | 40 GB | 143 |
| Muse-Glimmer-30B-bf16 | bf16 | 59.6 GB | 69 GB | 2.0K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| muse-glimmer-30b | macOS | 4-bit | FP16 | 128K |