GR

Granite Guardian 3.3 8b

GraniteGGUF by ibm-graniteUpdated 2025-08-12
Download on Hugging Face
Parameters8.17B
Context128K
Layers40
Architecturegranite
Smallest quant4.9 GB
Quick answer

Granite Guardian 3.3 8b needs about 6.8 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 4.9 GB (Q4_K_M) to 16.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Granite Guardian 3.3 8b – a specialized judging model for LLM outputs

Granite Guardian 3.3 8b is a hybrid thinking model that evaluates prompts and responses against criteria such as jailbreak attempts, profanity, and hallucinations. It can operate in thinking mode, producing reasoning traces, or non‑thinking mode, returning only a judgement score. The model is released under Apache 2.0.

Good at

  • Detecting jailbreak attempts
  • Assessing tool‑call hallucinations
  • Custom judging criteria

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is Apache 2.0

Best for

  • LLM safety monitoring
  • Agent‑based system validation
  • Custom policy enforcement

Who it’s for. Developers building LLM‑based applications who need automated content filtering and policy compliance. Researchers testing model behaviour against specific criteria may also use this model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.8 GB
Fits Get file →
Q5_K_M5.8 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.5 GB
Too big Get file →
Q8_08.7 GB 10.5 GB
Too big Get file →
F1616.3 GB 18.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.94 GB, estimated memory 6.8 GB at 8k context). If 12 GB VRAM is available, Q5_K_M (5.8 GB, 7.6 GB) or Q6_K (6.71 GB, 8.5 GB) are suitable. Higher precision quants require more memory.

What GPU do you need for Granite Guardian 3.3 8b?

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 Q5_K_M (5.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.3 GB file, about 18.2 GB in use).

Which Granite Guardian 3.3 8b quant should you choose?

Q4_K_M is the usual starting point for Granite Guardian 3.3 8b: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.7 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
Parameters8.17B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byibm-granite
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,307
Last updated2025-08-12

Frequently asked questions about Granite Guardian 3.3 8b

How much VRAM does Granite Guardian 3.3 8b need?

About 6.8 GB at Q4_K_M with an 8K context window. That is the 4.9 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 3.3 8b on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 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 3.3 8b GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, Q5_K_M is 5.8 GB, Q6_K is 6.7 GB, Q8_0 is 8.7 GB, F16 is 16.3 GB.

What context length does Granite Guardian 3.3 8b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Granite Guardian 3.3 8b GGUF?

The files are on Hugging Face in the ibm-granite/granite-guardian-3.3-8b-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 3.3 8b 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.

Can I run Granite Guardian 3.3 8b on 8 GB VRAM?

Yes, the Q4_K_M quantization requires approximately 6.8 GB of VRAM at 8k context, fitting within an 8 GB budget.

Does the model support vision tasks?

No, Granite Guardian 3.3 8b is a text‑only model and does not process images.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-guardian-3.3-8b

Similar models

Browse all →

More from ibm-granite

All by ibm-granite →

More Granite models

All Granite →

Other small models

All small models →