Muse-Glimmer-30B-Abliterated 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 10 quants, from 5.1 GB (F16) to 29.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Muse‑Glimmer‑30B‑Abliterated – a 27.9B‑parameter agentic model with vision and multimodal reasoning
Muse‑Glimmer‑30B‑Abliterated is a 27.9‑billion‑parameter causal language model with a dedicated perception encoder. It supports text and image input and is optimized for local deployment on consumer GPUs or CPUs.
Good at
- End‑to‑end agentic task completion
- Reliable tool use and failure recovery
- Multimodal reasoning with images
Limits
- Requires a recent llama.cpp master build
- No vision support without the mmproj projector
- Large memory footprint for higher‑bit quantizations
Best for
- Local autonomous agents
- Multimodal content analysis
- Offline tool‑driven workflows
Who it’s for. Developers building offline, agentic applications that need text and image understanding on a single GPU or CPU. The model is suitable for users who prefer a fully local, no‑cloud solution and can manage the required hardware and software stack.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 5.1 GB | 6.1 GB | Fits | Get file → | |
| Q2_K | 10.7 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_S | 12.5 GB | 13.4 GB | Too big | Get file → | |
| Q3_K_M | 13.7 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_S | 16.1 GB | 17.1 GB | Too big | Get file → | |
| Q4_K_M | 16.9 GB | 17.9 GB | Too big | Get file → | |
| Q5_K_S | 19.3 GB | 20.3 GB | Too big | Get file → | |
| Q5_K_M | 19.8 GB | 20.7 GB | Too big | Get file → | |
| Q6_K | 22.9 GB | 23.8 GB | Too big | Get file → | |
| Q8_0 | 29.6 GB | 30.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 16.94 GB, estimated 17.9 GB memory at 8 k context). For 12 GB VRAM, Q4_K_S (16.13 GB, 17.1 GB memory). For 16 GB VRAM, Q3_K_M (13.68 GB, 14.6 GB memory). Higher‑bit quantizations require more VRAM and RAM.
What GPU do you need for Muse-Glimmer-30B-Abliterated?
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: the best quant that fits is F16 (5.1 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (10.7 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (13.7 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (22.9 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.6 GB file, about 30.5 GB in use).
Which Muse-Glimmer-30B-Abliterated quant should you choose?
Q4_K_M is the usual starting point for Muse-Glimmer-30B-Abliterated: 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 F16 at 5.1 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Muse-Glimmer-30B-Abliterated
How much VRAM does Muse-Glimmer-30B-Abliterated 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-Abliterated on an 8 GB GPU?
Yes, with F16: 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-Abliterated GGUF?
It depends on the quant: F16 is 5.1 GB, Q2_K is 10.7 GB, Q3_K_S is 12.5 GB, Q3_K_M is 13.7 GB, Q4_K_S is 16.1 GB, Q4_K_M is 16.9 GB and 4 more.
What context length does Muse-Glimmer-30B-Abliterated 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-Abliterated GGUF?
The files are on Hugging Face in the cvgro/Muse-Glimmer-30B-Abliterated-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-Abliterated 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‑Abliterated on 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 17.9 GB memory at 8 k context, so 8 GB VRAM is insufficient. A higher‑bit quantization or more VRAM is needed.
Does this model support image input?
Yes, it has a dedicated perception encoder. Load the mmproj projector file along with the quantized model.
What license applies to this model?
The model is released under the Apache 2.0 license.