KA

KAT Dev 72B Exp

KatGGUF by FBTMAMLUpdated 2025-12-10
Download on Hugging Face
Parameters72.7B
Context128K
Layers80
Architectureqwen2
Smallest quant47.4 GB
Quick answer

KAT Dev 72B Exp needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 47.4 GB (Q4_K_M) to 145.4 GB (BF16). 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 FBTMAML. Its trained context length is 128K tokens. The repository has 3 quant files, from 47.4 GB (Q4_K_M) to 145.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M47.4 GB 50.6 GB
Too big Get file →
Q8_077.3 GB (5 parts) 80.4 GB
Too big Get file →
BF16145.4 GB (10 parts) 148.6 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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which KAT Dev 72B Exp quant should you choose?

Q4_K_M is the usual starting point for KAT Dev 72B Exp: it balances file size and quality well. Here it is a 47.4 GB file.

The Q8_0 file is 77.3 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters72.7B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byFBTMAML
FamilyKat
Licenseapache-2.0
Downloads (HF)12
Last updated2025-12-10

Frequently asked questions about KAT Dev 72B Exp

How much VRAM does KAT Dev 72B Exp need?

About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 KAT Dev 72B Exp on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 50.6 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: Q4_K_M is 47.4 GB, Q8_0 is 77.3 GB, BF16 is 145.4 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 FBTMAML/KAT-Dev-72B-Exp 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.

Other GGUFs of KAT-Dev-72B-Exp

Similar models

Browse all →

More from FBTMAML

All by FBTMAML →

More Kat models

All Kat →

Other large models

All large models →