Huihui granite 4.1 30b abliterated needs about 60.4 GB of memory at BF16 (a 57.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 57.7 GB (BF16) to 57.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Huihui granite 4.1 30b abliterated is a 28.9B-parameter Granite model in GGUF format, quantized by Momix-44. Its trained context length is 128K tokens. The repository has 2 quant files, from 57.7 GB (BF16) to 57.7 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 57.7 GB | 60.4 GB | Too big | Get file → | |
| BF16 | 57.7 GB | 60.4 GB | Too big | Get file → |
What GPU do you need for Huihui granite 4.1 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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Huihui granite 4.1 30b abliterated quant should you choose?
BF16 (57.7 GB) is the middle option in this repository. 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 Huihui granite 4.1 30b abliterated
How much VRAM does Huihui granite 4.1 30b abliterated need?
About 60.4 GB at BF16 with an 8K context window. That is the 57.7 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 Huihui granite 4.1 30b abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 60.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Huihui granite 4.1 30b abliterated GGUF?
It depends on the quant: BF16 is 57.7 GB, BF16 is 57.7 GB.
What context length does Huihui granite 4.1 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 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Huihui granite 4.1 30b abliterated GGUF?
The files are on Hugging Face in the Momix-44/Huihui-granite-4.1-30b-abliterated repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Huihui granite 4.1 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.