LL

Llama Guard 3 8B

LlamaGGUF by eaddarioUpdated 2025-04-25
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant3.3 GB
Quick answer

Llama Guard 3 8B needs about 6.0 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 13 quants, from 3.3 GB (Q3_K_S) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama Guard 3 8B – content safety classification model

Llama Guard 3 8B is a fine‑tuned Llama‑3.1‑8B model for content safety classification. It classifies prompts and responses, indicating safe or unsafe and listing violated categories. The model supports eight languages and is optimized for safety in search and code interpreter tool calls.

Good at

  • Prompt and response safety classification
  • Eight‑language support
  • Content category reporting

Limits

  • No vision support
  • Requires 8k context for estimates
  • License is llama3.1

Best for

  • Moderating user prompts
  • Filtering LLM outputs
  • Safety checks in code interpreters

Who it’s for. Developers building moderation layers for chat or search applications. Researchers testing safety classifiers on LLM outputs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.3 GB 4.9 GB
Fits Get file →
IQ3_S3.4 GB 5.0 GB
Fits Get file →
Q3_K_M3.6 GB 5.1 GB
Fits Get file →
IQ3_M3.7 GB 5.3 GB
Fits Get file →
Q3_K_L3.8 GB 5.3 GB
Fits Get file →
Q4_K_S4.3 GB 5.9 GB
Fits Get file →
IQ4_NL4.4 GB 6.0 GB
Fits Get file →
Q4_K_M4.4 GB 6.0 GB
Fits Get file →
Q5_K_S5.2 GB 6.8 GB
Fits Get file →
Q5_K_M5.4 GB 6.9 GB
Fits Get file →
Q6_K6.6 GB 8.1 GB
Too big Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (file size 4.28 GB, ~5.9 GB memory). For 12 GB VRAM use Q5_K_S (file size 5.24 GB, ~6.8 GB memory). For 16 GB VRAM use Q6_K (file size 6.57 GB, ~8.1 GB memory). Estimates are approximate.

What GPU do you need for Llama Guard 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: the best quant that fits is Q4_K_M (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.4 GB file, about 6.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which Llama Guard 3 8B quant should you choose?

Q4_K_M is the usual starting point for Llama Guard 3 8B: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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.

If memory is tight, the smallest file is Q3_K_S at 3.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byeaddario
FamilyLlama
Licensellama3.1
Downloads (HF)1,174
Last updated2025-04-25

Frequently asked questions about Llama Guard 3 8B

How much VRAM does Llama Guard 3 8B need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Llama Guard 3 8B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.4 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama Guard 3 8B GGUF?

It depends on the quant: Q3_K_S is 3.3 GB, IQ3_S is 3.4 GB, Q3_K_M is 3.6 GB, IQ3_M is 3.7 GB, Q3_K_L is 3.8 GB, Q4_K_S is 4.3 GB and 7 more.

What context length does Llama Guard 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Llama Guard 3 8B GGUF?

The files are on Hugging Face in the eaddario/Llama-Guard-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 Llama Guard 3 8B use?

Hugging Face lists the license as llama3.1. 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 Llama Guard 3 8B on 8 GB VRAM?

Yes, the Q4_K_S quantization requires about 5.9 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support image inputs?

No, the model has no vision capabilities.

What context length is needed for accurate classification?

The model was trained on 131072 tokens; 8k context is used for memory estimates.

Other GGUFs of Llama-Guard-3-8B

Similar models

Browse all →

More from eaddario

All by eaddario →

More Llama models

All Llama →

Other small models

All small models →