Muse Glimmer 30B_pruned needs about 17.3 GB of memory at Q4_K_M (a 16.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 7.5 GB (IQ2_XXS) to 53.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Muse Glimmer 30B_pruned – a 27‑billion‑parameter agentic LLM
Muse Glimmer 30B_pruned is a 27‑billion‑parameter causal language model. It is pruned to contain only Latin characters, reducing size by ~25%. The model supports reasoning, tool use, and multimodal input via a perception encoder.
Good at
- Multi‑step reasoning
- Reliable tool use
- Multimodal text‑image understanding
Limits
- Pruned, no emojis or non‑Latin output
- Requires llama.cpp > b10430
- Large VRAM needed for higher‑quality quants
Best for
- Agentic task completion
- Code debugging workflows
- Image‑text combined queries
Who it’s for. Developers building local autonomous agents who need robust reasoning and tool use without cloud dependency. The model is suitable for consumer hardware with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 7.5 GB | 8.4 GB | Too big | Get file → | |
| IQ2_XS | 8.3 GB | 9.2 GB | Too big | Get file → | |
| IQ2_S | 8.6 GB | 9.6 GB | Too big | Get file → | |
| IQ2_M | 9.3 GB | 10.3 GB | Too big | Get file → | |
| Q2_K_S | 9.5 GB | 10.5 GB | Too big | Get file → | |
| Q2_K | 10.2 GB | 11.1 GB | Too big | Get file → | |
| IQ3_XXS | 10.6 GB | 11.6 GB | Too big | Get file → | |
| IQ3_XS | 11.4 GB | 12.3 GB | Too big | Get file → | |
| Q3_K_S | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ3_S | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ3_M | 12.3 GB | 13.2 GB | Too big | Get file → | |
| Q3_K_M | 13.1 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_L | 14.1 GB | 15.1 GB | Too big | Get file → | |
| IQ4_XS | 14.6 GB | 15.6 GB | Too big | Get file → | |
| Q4_0 | 15.5 GB | 16.4 GB | Too big | Get file → | |
| Q4_K_S | 15.5 GB | 16.5 GB | Too big | Get file → | |
| Q4_K_M | 16.3 GB | 17.3 GB | Too big | Get file → | |
| Q4_1 | 17.0 GB | 18.0 GB | Too big | Get file → | |
| Q8_0 | 28.7 GB | 29.6 GB | Too big | Get file → | |
| BF16 | 53.9 GB | 54.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (7.5 GB) or IQ2_XS (8.26 GB). If 12 GB VRAM is available, Q4_K_M (16.32 GB) offers better quality. Higher quants like Q8_0 or BF16 require 28 GB+ VRAM and are not recommended for local runs.
What GPU do you need for Muse Glimmer 30B_pruned?
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: the best quant that fits is IQ3_XXS (10.6 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (14.6 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (17.0 GB file, about 18.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 29.6 GB in use).
Which Muse Glimmer 30B_pruned quant should you choose?
Q4_K_M is the usual starting point for Muse Glimmer 30B_pruned: it balances file size and quality well. Here it is a 16.3 GB file.
The Q8_0 file is 28.7 GB, about 1.8 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 IQ2_XXS at 7.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Muse Glimmer 30B_pruned
How much VRAM does Muse Glimmer 30B_pruned need?
About 17.3 GB at Q4_K_M with an 8K context window. That is the 16.3 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_pruned on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Muse Glimmer 30B_pruned GGUF?
It depends on the quant: IQ2_XXS is 7.5 GB, IQ2_XS is 8.3 GB, IQ2_S is 8.6 GB, IQ2_M is 9.3 GB, Q2_K_S is 9.5 GB, Q2_K is 10.2 GB and 14 more.
What context length does Muse Glimmer 30B_pruned 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_pruned GGUF?
The files are on Hugging Face in the bluevoid-pl/Muse-Glimmer-30B-pruned-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_pruned 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_pruned on 8 GB VRAM?
Yes, the IQ2_XXS quant uses 7.5 GB file size and estimates 8.4 GB VRAM at 8k context.
Does the pruned model support emojis?
No. The pruning removes emojis, so the model cannot output them.
What llama.cpp version is needed?
Use llama.cpp version greater than b10430 to avoid load failures.