Muse-Glimmer-30B needs about 19.6 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 13.8 GB (IQ3_S) to 21.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Muse‑Glimmer‑30B: multimodal dense causal LLM for autonomous agents
Muse‑Glimmer‑30B is a 27.9‑billion‑parameter causal language model with a dedicated perception encoder. It supports text and image inputs and is optimized for local deployment on consumer hardware.
Good at
- Multi‑step reasoning
- Reliable tool use
- Visual understanding
Limits
- No vision support in quantized versions
- Large VRAM requirement for full context
- Apache‑2.0 license restricts commercial redistribution
Best for
- Autonomous agent workflows
- Code generation and debugging
- Multimodal document analysis
Who it’s for. Developers building local autonomous agents that need reasoning, tool use, and visual input. The model runs without cloud access and is suitable for consumer‑grade GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 13.8 GB | 14.7 GB | Too big | Get file → | |
| IQ3_M | 14.1 GB | 15.0 GB | Too big | Get file → | |
| Q4_K_M | 18.6 GB | 19.6 GB | Too big | Get file → | |
| Q5_K_M | 21.8 GB | 22.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_S (13.77 GB file, 14.7 GB memory at 8 k context). For 12 GB VRAM, IQ3_M (14.1 GB file, 15 GB memory). For 16 GB VRAM, Q4_K_M (18.63 GB file, 19.6 GB memory). Estimates are approximate.
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ3_M (14.1 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (21.8 GB file, about 22.7 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 18.6 GB file.
If memory is tight, the smallest file is IQ3_S at 13.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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 19.6 GB at Q4_K_M with an 8K context window. That is the 18.6 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?
Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Muse-Glimmer-30B GGUF?
It depends on the quant: IQ3_S is 13.8 GB, IQ3_M is 14.1 GB, Q4_K_M is 18.6 GB, Q5_K_M is 21.8 GB.
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 vultr/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‑30B on 8 GB VRAM?
Use the IQ3_S quantization; it requires about 14.7 GB memory at 8 k context, which is close to 8 GB but may need swapping.
Does the model support image input?
Yes, the model includes a perception encoder for interleaved text and image inputs.
What license applies to the model?
The model is released under the Apache‑2.0 license.