AX

A.X K2

GGUFGGUF by sktUpdated 2026-08-19
Download on Hugging Face
Parameters690B
Context256K
Layers61
Architectureaxk2
Smallest quant370.4 GB
Quick answer

A.X K2 needs about 372.0 GB of memory at IQ4_XS (a 370.4 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 4.3 GB.

A.X K2 is a 690B-parameter model in GGUF format, quantized by skt. Its trained context length is 256K tokens. The repository has 1 quant file, from 370.4 GB (IQ4_XS) to 370.4 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS370.4 GB 372.0 GB
Too big Get file →

What GPU do you need for A.X K2?

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 A.X K2 quant should you choose?

IQ4_XS (370.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureaxk2
Parameters690B (approximate, mixture of experts)
Layers61
Trained context262,144 tokens
KV cache (fp16)130 KB per token

Source

Quantized byskt
Base modelskt/A.X-K2
Repositoryskt/A.X-K2-GGUF
Licenseapache-2.0
Downloads (HF)223
Last updated2026-08-19

Frequently asked questions about A.X K2

How much VRAM does A.X K2 need?

About 372.0 GB at IQ4_XS with an 8K context window. That is the 370.4 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 A.X K2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 372.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of A.X K2 GGUF?

It depends on the quant: IQ4_XS is 370.4 GB.

What context length does A.X K2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download A.X K2 GGUF?

The files are on Hugging Face in the skt/A.X-K2-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 A.X K2 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.

Similar models

Browse all →

Other large models

All large models →