GR

Granite Guardian 3.2 5b

GraniteGGUF by mrutkowsUpdated 2025-06-23
Download on Hugging Face
Parameters5.78B
Context128K
Layers28
Architecturegranite
Smallest quant3.5 GB
Quick answer

Granite Guardian 3.2 5b needs about 4.9 GB of memory at Q4_K_M (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 3.5 GB (Q4_K_M) to 11.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Granite Guardian 3.2 5b is a 5.78B-parameter Granite model in GGUF format, quantized by mrutkows. Its trained context length is 128K tokens. The repository has 5 quant files, from 3.5 GB (Q4_K_M) to 11.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M3.5 GB 4.9 GB
Fits Get file →
Q5_K_M4.1 GB 5.5 GB
Fits Get file →
Q6_K4.7 GB 6.2 GB
Fits Get file →
Q8_06.1 GB 7.6 GB
Tight Get file →
F1611.6 GB 13.0 GB
Too big Get file →

What GPU do you need for Granite Guardian 3.2 5b?

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 Q5_K_M (4.1 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.1 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (6.1 GB file, about 7.6 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (11.6 GB file, about 13.0 GB in use).

Which Granite Guardian 3.2 5b quant should you choose?

Q4_K_M is the usual starting point for Granite Guardian 3.2 5b: it balances file size and quality well. Here it is a 3.5 GB file.

The Q8_0 file is 6.1 GB, about 1.8 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

Architecturegranite
Parameters5.78B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymrutkows
FamilyGranite
Licenseapache-2.0
Downloads (HF)9
Last updated2025-06-23

Frequently asked questions about Granite Guardian 3.2 5b

How much VRAM does Granite Guardian 3.2 5b need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 3.5 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 Guardian 3.2 5b on an 8 GB GPU?

Yes, with Q8_0: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite Guardian 3.2 5b GGUF?

It depends on the quant: Q4_K_M is 3.5 GB, Q5_K_M is 4.1 GB, Q6_K is 4.7 GB, Q8_0 is 6.1 GB, F16 is 11.6 GB.

What context length does Granite Guardian 3.2 5b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Granite Guardian 3.2 5b GGUF?

The files are on Hugging Face in the mrutkows/granite-guardian-3.2-5b-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 Guardian 3.2 5b 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 from mrutkows

All by mrutkows →

More Granite models

All Granite →

Other small models

All small models →