GR

Granite Swash 3b A600M

GraniteGGUF by emredeveloperUpdated 2026-08-13
Download on Hugging Face
Parameters3.02B
Context8K
Layers28
Architecturegranite_swa
Smallest quant6.0 GB
Quick answer

Granite Swash 3b A600M needs about 6.8 GB of memory at BF16 (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU.

Granite Swash 3b A600M is a 3.02B-parameter Granite model in GGUF format, quantized by emredeveloper. Its trained context length is 8K tokens. The repository has 1 quant file, from 6.0 GB (BF16) to 6.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF166.0 GB 6.8 GB
Fits Get file →

What GPU do you need for Granite Swash 3b A600M?

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: the best quant that fits is BF16 (6.0 GB file, about 6.8 GB in use).

Which Granite Swash 3b A600M quant should you choose?

BF16 (6.0 GB) is the middle option in this repository. 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

Architecturegranite_swa
Parameters3.02B (approximate, mixture of experts)
Layers28
Trained context8,192 tokens
KV cache (fp16)28 KB per token

Source

Quantized byemredeveloper
FamilyGranite
Licenseapache-2.0
Downloads (HF)43
Last updated2026-08-13

Frequently asked questions about Granite Swash 3b A600M

How much VRAM does Granite Swash 3b A600M need?

About 6.8 GB at BF16 with an 8K context window. That is the 6.0 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 Granite Swash 3b A600M on an 8 GB GPU?

Yes, with BF16: the 6.0 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite Swash 3b A600M GGUF?

It depends on the quant: BF16 is 6.0 GB.

What context length does Granite Swash 3b A600M support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download Granite Swash 3b A600M GGUF?

The files are on Hugging Face in the emredeveloper/granite-swash-3b-a600m-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 Granite Swash 3b A600M 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 →

More Granite models

All Granite →

Other tiny models

All tiny models →