IceCannon needs about 11.4 GB of memory at its main file (a 9.8 GB file) with an 8K context window, so it fits on a 12 GB GPU.
IceCannon is a 16.4B-parameter Icecannon model in GGUF format, quantized by eddy1111111. The repository has 1 quant file, from 9.8 GB to 9.8 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 9.8 GB | 11.4 GB | Too big | Get file → |
What GPU do you need for IceCannon?
These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (9.8 GB file, about 11.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about IceCannon
How much VRAM does IceCannon need?
About 11.4 GB at its main file with an 8K context window. That is the 9.8 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 IceCannon on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of IceCannon GGUF?
It depends on the quant: file is 9.8 GB.
Where can I download IceCannon GGUF?
The files are on Hugging Face in the eddy1111111/IceCannon repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does IceCannon 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.