Muse-Glimmer-30B needs about 17.9 GB of memory at Q4_K_M (a 16.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 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.
Muse‑Glimmer‑30B: 27.9B‑parameter multimodal LLM for autonomous agents
Muse‑Glimmer‑30B is a 27.9‑billion‑parameter causal language model with a dedicated perception encoder. It supports reasoning, tool use, and vision in a single local model. The model is released under Apache‑2.0 and trained on 131072 context tokens.
Good at
- Multimodal reasoning with text and images
- Reliable tool invocation
- End‑to‑end agentic task completion
Limits
- No vision support on older builds
- Requires 8k context for memory estimates
- Large VRAM needed for higher‑quality quants
Best for
- Local autonomous agents
- Multimodal content analysis
- Tool‑driven workflow automation
Who it’s for. Developers building local AI agents that need reasoning, tool use, and image understanding without cloud access. The model is suitable for consumer hardware with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| BF16 | 5.1 GB | 6.1 GB | Fits | Get file → | |
| IQ2_XXS | 9.3 GB | 10.2 GB | Too big | Get file → | |
| IQ2_M | 9.8 GB | 10.8 GB | Too big | Get file → | |
| IQ3_XXS | 11.1 GB | 12.1 GB | Too big | Get file → | |
| IQ2_M | 11.2 GB | 12.1 GB | Too big | Get file → | |
| IQ3_XXS | 12.2 GB | 13.2 GB | Too big | Get file → | |
| IQ3_M | 14.9 GB | 15.9 GB | Too big | Get file → | |
| IQ4_XS | 15.2 GB | 16.2 GB | Too big | Get file → | |
| IQ4_XS | 15.9 GB | 16.9 GB | Too big | Get file → | |
| IQ4_XS | 16.0 GB | 17.0 GB | Too big | Get file → | |
| Q4_K_M | 16.9 GB | 17.9 GB | Too big | Get file → | |
| Q4_K_M | 19.1 GB | 20.0 GB | Too big | Get file → | |
| Q5_K_M | 22.7 GB | 23.6 GB | Too big | Get file → | |
| Q6_K | 28.3 GB | 29.2 GB | Too big | Get file → | |
| Q8_0 | 29.6 GB | 30.5 GB | Too big | Get file → | |
| Q8_0 | 30.9 GB | 31.8 GB | Too big | Get file → | |
| Q8_0 | 30.9 GB | 31.8 GB | Too big | Get file → | |
| Q8_0 | 32.1 GB | 33.1 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 (file size 16.94 GB, ~17.9 GB memory at 8k context). For 12‑GB VRAM use Q5_K_M (22.67 GB, ~23.6 GB). For 24‑GB VRAM use Q8_0 (29.61 GB, ~30.5 GB). 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: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.1 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_M (9.8 GB file, about 10.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (14.9 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (22.7 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (30.9 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (32.1 GB file, about 33.1 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 16.9 GB file.
The Q8_0 file is 29.6 GB, about 1.7 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 17.9 GB at Q4_K_M with an 8K context window. That is the 16.9 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 BF16: the 5.1 GB file needs about 6.1 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, BF16 is 5.1 GB, IQ2_XXS is 9.3 GB, IQ2_M is 9.8 GB, IQ3_XXS is 11.1 GB, IQ2_M is 11.2 GB and 14 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 AtomicChat/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 Q4_K_M quant; it requires about 17.9 GB of VRAM at 8k context, so 8 GB is insufficient.
Does the model support vision?
Yes, it has a dedicated perception encoder for interleaved text and images.
What license applies?
The model is released under Apache‑2.0.