skt_A.X 4.0 needs about 147.0 GB of memory at F16 (a 143.8 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 10.7 GB.
skt_A.X 4.0 is a 71.9B-parameter Skt model in GGUF format, quantized by suitup91. Its trained context length is 128K tokens. The repository has 1 quant file, from 143.8 GB (F16) to 143.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 143.8 GB | 147.0 GB | Too big | Get file → |
What GPU do you need for skt_A.X 4.0?
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 skt_A.X 4.0 quant should you choose?
F16 (143.8 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 skt_A.X 4.0
How much VRAM does skt_A.X 4.0 need?
About 147.0 GB at F16 with an 8K context window. That is the 143.8 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 skt_A.X 4.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 147.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of skt_A.X 4.0 GGUF?
It depends on the quant: F16 is 143.8 GB.
What context length does skt_A.X 4.0 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download skt_A.X 4.0 GGUF?
The files are on Hugging Face in the suitup91/skt_A.X-4.0_Heretic-f16-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 skt_A.X 4.0 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.