Granite Guardian 3.2 3b A800M needs about 3.1 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 2.0 GB (Q4_K_M) to 6.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Granite Guardian 3.2 3b A800M – risk‑detection LLM
Granite Guardian 3.2 3b A800M is a fine‑tuned Granite 3.2 3B-A800M instruct model. It detects risks in prompts, responses, and conversations. The model is trained on human annotations and synthetic data from internal red‑teaming.
Good at
- Risk detection in prompts and responses
- Assessing RAG relevance and groundedness
- Function‑calling risk evaluation
Limits
- No vision support
- Requires 131072 token context
- Apache 2.0 license
Best for
- Enterprise risk guardrails
- RAG quality assurance
- Agentic workflow safety
Who it’s for. Developers building safe LLM applications that need prompt, response, and conversation risk detection. Suitable for enterprises requiring compliance and risk monitoring.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.0 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.4 GB | Fits | Get file → | |
| Q6_K | 2.7 GB | 3.8 GB | Fits | Get file → | |
| Q8_0 | 3.5 GB | 4.5 GB | Fits | Get file → | |
| F16 | 6.6 GB | 7.6 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.02 GB, estimated 3.1 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (2.36 GB, 3.4 GB memory). For 16 GB VRAM, Q6_K (2.71 GB, 3.8 GB memory). Higher‑precision quants need more memory.
What GPU do you need for Granite Guardian 3.2 3b A800M?
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 Q6_K (2.7 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.5 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 7.6 GB in use).
Which Granite Guardian 3.2 3b A800M quant should you choose?
Q4_K_M is the usual starting point for Granite Guardian 3.2 3b A800M: it balances file size and quality well. Here it is a 2.0 GB file.
The Q8_0 file is 3.5 GB, about 1.7 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
Frequently asked questions about Granite Guardian 3.2 3b A800M
How much VRAM does Granite Guardian 3.2 3b A800M need?
About 3.1 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Guardian 3.2 3b A800M on an 8 GB GPU?
Yes, with F16: the 6.6 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 3b A800M GGUF?
It depends on the quant: Q4_K_M is 2.0 GB, Q5_K_M is 2.4 GB, Q6_K is 2.7 GB, Q8_0 is 3.5 GB, F16 is 6.6 GB.
What context length does Granite Guardian 3.2 3b A800M support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download Granite Guardian 3.2 3b A800M GGUF?
The files are on Hugging Face in the ibm-research/granite-guardian-3.2-3b-a800m-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 3b A800M 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 3.2 3b A800M on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 3.1 GB memory at 8k context, fitting within 8 GB VRAM.
Does the model support vision or audio input?
No, the model only processes text and has no vision or audio capabilities.
What license applies to this model?
The model is released under the Apache 2.0 license.