What are the hardware requirements for LlamaGuard 7B?

LlamaGuard 7B requires approximately 13.5 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LlamaGuard 7B and how large is it?

LlamaGuard 7B is developed by meta-llama, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate LlamaGuard 7B?

LlamaGuard 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LlamaGuard 7B by meta-llama — VRAM 13.5GB, 4K context

Name: LlamaGuard 7B
Author: meta-llama

LlamaGuard 7B is an open-source language model by meta-llama. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: llama2, LLM Explorer Score: 0.13.

Arxiv:2307.09288 Arxiv:2312.04724 Conversational En Endpoints compatible Facebook Llama Llama2 Meta Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/meta-llama/LlamaGuard-7b

LlamaGuard 7B Parameters and Internals

Model Type

input-output safeguard, content classification

Use Cases

Primary Use Cases:

Classifying content in LLM inputs and responses

Training Details

Data Sources:

Anthropic dataset, in-house redteaming examples

Data Volume:

~13K training examples

LLM Name	LlamaGuard 7B
Repository 🤗	https://huggingface.co/meta-llama/LlamaGuard-7b
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-07-05
Maintainer	meta-llama
Model Type	llama
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.6 GB: 3-of-3
Supported Languages	en
Model Architecture	AutoModelForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the LlamaGuard 7B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the LlamaGuard 7B

Model	Likes	Downloads	VRAM
...B GPTQ 4bit 128g Actorder True	2	6	2 GB

Best Alternatives to LlamaGuard 7B

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 7B V0.3	32K / 14.5 GB	1366	5
Mistral 7B Instruct V0.3	32K / 14.5 GB	91	6
...unoichi Lemon Royale V3 32K 7B	32K / 14.5 GB	11	5
Mistral 7B Instruct V0.3	32K / 14.5 GB	1122	3
Mistralai Mistral 7B V0.3	32K / 14.5 GB	6	3
...ralai Mistral 7B Instruct V0.3	32K / 14.5 GB	6	3
Mistral 7B Instruct V0.3	32K / 14.5 GB	6	0
Mistral 7B V0.2	32K / 14.5 GB	66	1
Full V4 Astromistral Final	32K / 4.5 GB	6	1
Merak 7B Squadpairs Indo	4K / 7 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than meta-llama/LlamaGuard-7b.