Muse Glimmer 30B needs about 18.2 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 30 quants, from 0.0 GB to 55.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
30B Muse Glimmer, multimodal LLM for local autonomous agents
Muse Glimmer 30B is a 30‑billion‑parameter causal language model with a dedicated perception encoder. It supports text and image input and is optimized for local deployment on consumer hardware. The model is released under Apache 2.0 and can be run with llama.cpp.
Good at
- Multimodal reasoning with text and images
- End‑to‑end agentic task completion
- Reliable tool use and failure recovery
Limits
- Requires 8‑k context for memory estimates
- Large model size limits low‑VRAM devices
- No built‑in vision support without mmproj file
Best for
- Building local autonomous agents
- Multimodal content analysis
- Complex multi‑step reasoning tasks
Who it’s for. Developers and researchers who need a multimodal LLM that can run locally without cloud access. The model is suitable for building autonomous agents and complex reasoning workflows on consumer hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 3.7 GB | Fits | Get file → | |
| IQ2_XXS | 8.9 GB | 9.9 GB | Too big | Get file → | |
| IQ2_XS | 9.6 GB | 10.5 GB | Too big | Get file → | |
| IQ2_S | 10.0 GB | 11.0 GB | Too big | Get file → | |
| IQ2_M | 10.7 GB | 11.6 GB | Too big | Get file → | |
| Q2_K | 11.0 GB | 12.0 GB | Too big | Get file → | |
| IQ3_XXS | 11.5 GB | 12.5 GB | Too big | Get file → | |
| IQ3_XS | 12.3 GB | 13.3 GB | Too big | Get file → | |
| Q2_K_L | 12.3 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_S | 12.8 GB | 13.7 GB | Too big | Get file → | |
| IQ3_M | 13.1 GB | 14.0 GB | Too big | Get file → | |
| Q3_K_M | 14.0 GB | 14.9 GB | Too big | Get file → | |
| Q3_K_L | 14.8 GB | 15.7 GB | Too big | Get file → | |
| IQ4_XS | 15.4 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_XL | 16.0 GB | 16.9 GB | Too big | Get file → | |
| IQ4_NL | 16.2 GB | 17.2 GB | Too big | Get file → | |
| Q4_0 | 16.3 GB | 17.2 GB | Too big | Get file → | |
| Q4_K_S | 16.3 GB | 17.3 GB | Too big | Get file → | |
| Q4_K_M | 17.3 GB | 18.2 GB | Too big | Get file → | |
| Q4_1 | 17.8 GB | 18.8 GB | Too big | Get file → | |
| Q4_K_L | 18.3 GB | 19.2 GB | Too big | Get file → | |
| Q5_K_S | 19.4 GB | 20.4 GB | Too big | Get file → | |
| Q5_K_M | 20.1 GB | 21.0 GB | Too big | Get file → | |
| Q5_K_L | 20.9 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 23.4 GB | 24.4 GB | Too big | Get file → | |
| Q6_K_L | 24.1 GB | 25.0 GB | Too big | Get file → | |
| Q8_0 | 29.6 GB | 30.5 GB | Too big | Get file → | |
| BF16 | 55.7 GB (2 parts) | 56.7 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_M (17.31 GB) or Q4_0 (16.27 GB). For 12‑GB VRAM, Q4_K_L (18.3 GB) or Q5_K_S (19.44 GB) are suitable. Larger VRAM allows higher‑precision quants such as Q5_K_L (20.94 GB) or Q6_K (23.41 GB).
What GPU do you need for Muse Glimmer 30B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (11.0 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (14.8 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_L (20.9 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.6 GB file, about 30.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (29.6 GB file, about 30.5 GB in use).
Which Muse Glimmer 30B quant should you choose?
Q4_K_M is the usual starting point for Muse Glimmer 30B: it balances file size and quality well. Here it is a 17.3 GB file.
The Q8_0 file is 2.7 GB, about 0.2 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Muse Glimmer 30B
How much VRAM does Muse Glimmer 30B need?
About 18.2 GB at Q4_K_M with an 8K context window. That is the 17.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Muse Glimmer 30B on an 8 GB GPU?
Yes, with Q8_0: the 2.7 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Muse Glimmer 30B GGUF?
It depends on the quant: file is 0.0 GB, Q4_0 is 1.5 GB, Q8_0 is 2.7 GB, IQ2_XXS is 8.9 GB, IQ2_XS is 9.6 GB, IQ2_S is 10.0 GB and 24 more.
What context length does Muse Glimmer 30B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download Muse Glimmer 30B GGUF?
The files are on Hugging Face in the bartowski/Muse-Glimmer-30B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Muse Glimmer 30B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Muse Glimmer on 8 GB VRAM?
Yes, the Q4_K_M quant is 17.31 GB, which fits within 8 GB VRAM when using efficient memory management and a small context.
Does the model support image input?
Yes, Muse Glimmer includes a perception encoder and requires the mmproj file for image processing.
What license applies to this model?
The model is released under the Apache 2.0 license.