SplitUntied needs about 50.1 GB of memory at its main file (a 17.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
SplitUntied is a 32.1B-parameter Llama model in GGUF format, quantized by Austriani. Its trained context length is 256K tokens. The repository has 1 quant file, from 17.4 GB to 17.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 17.4 GB | 50.1 GB | Too big | Get file → |
What GPU do you need for SplitUntied?
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.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SplitUntied
How much VRAM does SplitUntied need?
About 50.1 GB at its main file with an 8K context window. That is the 17.4 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 SplitUntied on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 50.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SplitUntied GGUF?
It depends on the quant: file is 17.4 GB.
What context length does SplitUntied support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download SplitUntied GGUF?
The files are on Hugging Face in the Austriani/Split-Untied-31B-MaxOptimaV2-ik_llama.cpp repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SplitUntied 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.