Local LLM model page

Llama Guard 3 (8B)

Meta's content safety classifier. Detect unsafe content in LLM outputs. 86K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
8B
Minimum RAM
8 GB
Model size
4.7 GB
Quantization
Q5_K_M

Can Llama Guard 3 (8B) run locally?

Llama Guard 3 (8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: llama-guard-3-8b

Hugging Face repository: meta-llama/Llama-Guard-3-8B-GGUF

standard

Strengths

  • Meta's content safety classifier. Detect unsafe content in LLM outputs. 86K downloads.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • standard

Benchmarks

Speed: 8/10

Quality: 6/10

Coding: 2/10

Reasoning: 5/10

Technical details

Developer: llama

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-09