KAT Dev 72B Exp needs about 32.5 GB of memory at IQ2_M (a 29.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 25.5 GB (IQ2_XXS) to 39.7 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
KAT Dev 72B Exp is a 72.7B-parameter Kat model in GGUF format, quantized by richardyoung. Its trained context length is 128K tokens. The repository has 4 quant files, from 25.5 GB (IQ2_XXS) to 39.7 GB (IQ4_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 25.5 GB | 28.7 GB | Too big | Get file → | |
| IQ2_M | 29.3 GB | 32.5 GB | Too big | Get file → | |
| IQ3_M | 35.5 GB | 38.7 GB | Too big | Get file → | |
| IQ4_XS | 39.7 GB | 42.9 GB | Too big | Get file → |
What GPU do you need for KAT Dev 72B Exp?
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: the best quant that fits is IQ2_XXS (25.5 GB file, about 28.7 GB in use).
- 48 GB VRAM: the best quant that fits is IQ4_XS (39.7 GB file, about 42.9 GB in use).
Which KAT Dev 72B Exp quant should you choose?
IQ2_M (29.3 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is IQ2_XXS at 25.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about KAT Dev 72B Exp
How much VRAM does KAT Dev 72B Exp need?
About 32.5 GB at IQ2_M with an 8K context window. That is the 29.3 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 KAT Dev 72B Exp on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 28.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of KAT Dev 72B Exp GGUF?
It depends on the quant: IQ2_XXS is 25.5 GB, IQ2_M is 29.3 GB, IQ3_M is 35.5 GB, IQ4_XS is 39.7 GB.
What context length does KAT Dev 72B Exp 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 KAT Dev 72B Exp GGUF?
The files are on Hugging Face in the richardyoung/kat-dev-72b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does KAT Dev 72B Exp 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.