AN

anthill

AnthillGGUF by skreling-engUpdated 2026-06-27
Download on Hugging Face
Parameters4.99B
Context32K
Layers28
Architectureqwen2
Smallest quant0.3 GB
Quick answer

anthill needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.3 GB (BF16) to 22.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

anthill is a 4.99B-parameter Anthill model in GGUF format, quantized by skreling-eng. Its trained context length is 32K tokens. The repository has 12 quant files, from 0.3 GB (BF16) to 22.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF160.3 GB 1.1 GB
Fits Get file →
Q4_K_M1.0 GB 1.7 GB
Fits Get file →
—1.0 GB 1.7 GB
Fits Get file →
BF161.2 GB 1.9 GB
Fits Get file →
—1.6 GB 2.4 GB
Fits Get file →
—1.6 GB 2.4 GB
Fits Get file →
—5.1 GB 5.8 GB
Fits Get file →
Q4_K_M9.0 GB 9.7 GB
Too big Get file →
—9.0 GB 9.7 GB
Too big Get file →
BF1610.0 GB 10.7 GB
Too big Get file →
BF1610.0 GB 10.7 GB
Too big Get file →
—22.1 GB 22.9 GB
Too big Get file →

What GPU do you need for anthill?

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: the best quant that fits is the main file (1.6 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (5.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.1 GB file, about 5.8 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (10.0 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (10.0 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (22.1 GB file, about 22.9 GB in use).

Which anthill quant should you choose?

Q4_K_M is the usual starting point for anthill: it balances file size and quality well. Here it is a 1.0 GB file.

If memory is tight, the smallest file is BF16 at 0.3 GB, with the quality trade-offs that come with fewer bits. 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

Architectureqwen2
Parameters4.99B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized byskreling-eng
FamilyAnthill
Licenseapache-2.0
Downloads (HF)219
Last updated2026-06-27

Frequently asked questions about anthill

How much VRAM does anthill need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 anthill on an 8 GB GPU?

Yes, with the smaller files: the 5.1 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of anthill GGUF?

It depends on the quant: BF16 is 0.3 GB, Q4_K_M is 1.0 GB, file is 1.0 GB, BF16 is 1.2 GB, file is 1.6 GB, file is 1.6 GB and 6 more.

What context length does anthill support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download anthill GGUF?

The files are on Hugging Face in the skreling-eng/anthill repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does anthill 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 small models

All small models →