Muse Glimmer 30B Abliterated needs about 2.3 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 1.6 GB (Q4_K_M) to 29.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
Muse Glimmer 30B Abliterated – 28B DFlash model with vision and text generation
Muse Glimmer 30B Abliterated is a 28‑billion‑parameter DFlash architecture model. It supports vision input and speculative decoding. The model is available in a full quant ladder and a compact Q4_K_M version for low‑memory use.
Good at
- Vision input and text generation
- Speculative decoding
- Runs on single consumer GPU or CPU
Limits
- Large context size of 131072 tokens
- Requires 8‑k context memory estimates up to 30.3 GB for Q8_0
- Experimental release with potential edge‑case issues
Best for
- Local on‑device inference
- Image‑guided text generation
- Low‑latency single‑GPU workloads
Who it’s for. Developers and researchers needing a local, vision‑capable LLM that can run on a single GPU or CPU. The model is suitable for offline applications where privacy and low latency are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.6 GB | 2.3 GB | Fits | Get file → | |
| F16 | 5.1 GB | 5.8 GB | Fits | Get file → | |
| Q2_K | 10.7 GB | 11.4 GB | Too big | Get file → | |
| Q3_K_S | 12.5 GB | 13.2 GB | Too big | Get file → | |
| Q3_K_M | 13.7 GB | 14.3 GB | Too big | Get file → | |
| Q4_K_S | 16.1 GB | 16.8 GB | Too big | Get file → | |
| Q4_K_M | 16.9 GB | 17.6 GB | Too big | Get file → | |
| Q5_K_S | 19.3 GB | 20.0 GB | Too big | Get file → | |
| Q5_K_M | 19.8 GB | 20.5 GB | Too big | Get file → | |
| Q6_K | 22.9 GB | 23.5 GB | Too big | Get file → | |
| Q8_0 | 29.6 GB | 30.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (1.63 GB file, ~2.3 GB memory at 8 k context). For 16 GB VRAM, Q4_K_S (16.13 GB file, ~16.8 GB memory) or Q5_K_S (19.35 GB file, ~20 GB memory). For 32 GB VRAM, Q8_0 (29.61 GB file, ~30.3 GB memory) gives full precision.
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: the best quant that fits is Q4_K_M (1.6 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (5.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.1 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (10.7 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (13.7 GB file, about 14.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (22.9 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.6 GB file, about 30.3 GB in use).
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 1.6 GB file.
The Q8_0 file is 29.6 GB, about 18.2 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Muse Glimmer 30B Abliterated
How much VRAM does Muse Glimmer 30B Abliterated need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.6 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 5.8 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: Q4_K_M is 1.6 GB, 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 and 5 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 0.2 GB at 8K and 0.7 GB at 32K.
Where can I download Muse Glimmer 30B Abliterated GGUF?
The files are on Hugging Face in the The-freezer/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?
Yes, the Q4_K_M quant is 1.63 GB and requires about 2.3 GB memory at 8 k context, fitting within 8 GB VRAM.
Does the model support image input?
Yes, vision is detected. Load a text quant plus an mmproj projector for image input.
Is the model free to use?
The model is licensed under Apache‑2.0, allowing free use and modification.