Muse Glimmer 30B ROCmFPX needs about 15.9 GB of memory at its main file (a 15.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 1.5 GB to 28.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
Muse Glimmer 30B ROCmFPX – 27.9B parameter multimodal LLM for local autonomous agents
Muse Glimmer 30B ROCmFPX is a 27.9‑billion‑parameter causal language model with a dedicated perception encoder. It supports vision, multi‑step reasoning, tool use, and failure recovery. The model is optimized for local deployment on AMD Strix Halo GPUs.
Good at
- Vision‑enabled multimodal reasoning
- End‑to‑end agentic task completion
- Reliable tool use and failure recovery
Limits
- Requires patched ROCmFPX build
- No support for other GPU architectures
- Large memory footprint for full context
Best for
- Local autonomous agents
- Multimodal content analysis
- Complex workflow automation
Who it’s for. Developers building local AI agents that need vision and advanced reasoning without cloud dependency. The model is suitable for consumer hardware with AMD Strix Halo GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.5 GB | 2.2 GB | Fits | Get file → | |
| — | 2.6 GB | 3.3 GB | Fits | Get file → | |
| — | 15.2 GB | 15.9 GB | Too big | Get file → | |
| — | 16.0 GB | 16.7 GB | Too big | Get file → | |
| — | 28.7 GB | 29.4 GB | Too big | Get file → |
For 8 GB VRAM, use the 1.49 GB file; it requires ~2.2 GB memory at 8 k context. For 16 GB VRAM, the 16.03 GB file uses ~16.7 GB memory. For larger budgets, the 28.74 GB file uses ~29.4 GB memory. Estimates are approximate.
What GPU do you need for Muse Glimmer 30B ROCmFPX?
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 (2.6 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (2.6 GB file, about 3.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (2.6 GB file, about 3.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (2.6 GB file, about 3.3 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (15.2 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (16.0 GB file, about 16.7 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (28.7 GB file, about 29.4 GB in use).
Which Muse Glimmer 30B ROCmFPX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 1.5 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 ROCmFPX
How much VRAM does Muse Glimmer 30B ROCmFPX need?
About 15.9 GB at its main file with an 8K context window. That is the 15.2 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 ROCmFPX on an 8 GB GPU?
Yes, with the smaller files: the 2.6 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Muse Glimmer 30B ROCmFPX GGUF?
It depends on the quant: file is 1.5 GB, file is 2.6 GB, file is 15.2 GB, file is 16.0 GB, file is 28.7 GB.
What context length does Muse Glimmer 30B ROCmFPX 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 ROCmFPX GGUF?
The files are on Hugging Face in the vmlinux/Muse-Glimmer-30B-ROCmFPX-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 ROCmFPX 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 ROCmFPX on 8 GB VRAM?
The 1.49 GB file requires about 2.2 GB memory at 8 k context, so it fits on 8 GB VRAM with headroom for other processes.
What build is needed to run the ROCmFPX files?
A patched build of charlie12345/ROCmFPX with the ROCmFPX‑Muse‑Glimmer.patch applied is required; stock llama.cpp does not support these layouts.
Does the model support vision?
Yes, it includes a dedicated perception encoder for interleaved text and image input.