Muse Glimmer 30B needs about 14.8 GB of memory at IQ3_M (a 14.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 16 quants, from 1.6 GB to 55.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
Muse Glimmer 30B is a 27.9B-parameter Muse model in GGUF format, quantized by vs4vijay. Its trained context length is 128K tokens. The repository has 16 quant files, from 1.6 GB to 55.7 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.6 GB | 2.3 GB | Fits | Get file → | |
| IQ2_XXS | 10.7 GB | 11.4 GB | Too big | Get file → | |
| IQ2_XS | 11.5 GB | 12.2 GB | Too big | Get file → | |
| IQ2_M | 12.3 GB | 12.9 GB | Too big | Get file → | |
| Q2_K_XL | 12.4 GB | 13.1 GB | Too big | Get file → | |
| IQ3_XXS | 13.1 GB | 13.8 GB | Too big | Get file → | |
| Q3_K_XL | 13.4 GB | 14.0 GB | Too big | Get file → | |
| IQ3_M | 14.1 GB | 14.8 GB | Too big | Get file → | |
| Q4_K_XL | 15.9 GB | 16.5 GB | Too big | Get file → | |
| Q5_K_M | 19.2 GB | 19.9 GB | Too big | Get file → | |
| Q5_K_L | 19.8 GB | 20.4 GB | Too big | Get file → | |
| Q5_K_XL | 21.8 GB | 22.5 GB | Too big | Get file → | |
| Q6_K_XL | 26.3 GB | 26.9 GB | Too big | Get file → | |
| Q8_0 | 29.6 GB | 30.3 GB | Too big | Get file → | |
| Q8_K_XL | 32.3 GB | 33.0 GB | Too big | Get file → | |
| BF16 | 55.7 GB (2 parts) | 56.4 GB | Too big | Get file → |
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 (1.6 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (1.6 GB file, about 2.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (1.6 GB file, about 2.3 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XXS (10.7 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (14.1 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_XL (21.8 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.6 GB file, about 30.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (32.3 GB file, about 33.0 GB in use).
Which Muse Glimmer 30B quant should you choose?
IQ3_M (14.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is the first one in the table at 1.6 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 14.8 GB at IQ3_M with an 8K context window. That is the 14.1 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 the smaller files: the 1.6 GB file needs about 2.3 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 1.6 GB, IQ2_XXS is 10.7 GB, IQ2_XS is 11.5 GB, IQ2_M is 12.3 GB, Q2_K_XL is 12.4 GB, IQ3_XXS is 13.1 GB and 10 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 0.2 GB at 8K and 0.7 GB at 32K.
Where can I download Muse Glimmer 30B GGUF?
The files are on Hugging Face in the vs4vijay/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.