GR

swarm

GraniteGGUF by dongzi01Updated 2025-10-13
Download on Hugging Face
Parameters8.19B
Context128K
Layers36
Architectureqwen3
Smallest quant2.4 GB
Quick answer

swarm needs about 4.1 GB of memory at IQ1_M (a 2.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

swarm is a 8.19B-parameter Granite model in GGUF format, quantized by dongzi01. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.4 GB (IQ1_M) to 2.4 GB (IQ1_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M2.4 GB 4.1 GB
Fits Get file →

What GPU do you need for swarm?

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: the best quant that fits is IQ1_M (2.4 GB file, about 4.1 GB in use).

Which swarm quant should you choose?

IQ1_M (2.4 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters8.19B
Layers36
Trained context131,072 tokens
KV cache (fp16)144 KB per token

Source

Quantized bydongzi01
FamilyGranite
Repositorydongzi01/swarm
Licenseapache-2.0
Downloads (HF)21
Last updated2025-10-13

Frequently asked questions about swarm

How much VRAM does swarm need?

About 4.1 GB at IQ1_M with an 8K context window. That is the 2.4 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 swarm on an 8 GB GPU?

Yes, with IQ1_M: the 2.4 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of swarm GGUF?

It depends on the quant: IQ1_M is 2.4 GB.

What context length does swarm support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download swarm GGUF?

The files are on Hugging Face in the dongzi01/swarm repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does swarm 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 granite-docling-258M

Similar models

Browse all →

More Granite models

All Granite →

Other small models

All small models →