SafetyCheck exact model cardOpen weights where releasedUpdated 2026

Llama Guard 3

Meta · Llama

Llama Guard 3 is positioned for safety classification and guardrail workflows around Llama-family applications.

Best for

Safety checks, guardrail experiments, and policy classification workflows.

Tradeoffs

Verify license, deployment requirements, runtime support, and fit on your own workload before production use.

Local hardware notes

Local hardware needs vary by size, quantization, and runtime. Check the exact model card and serving stack.

Local workflow notes

Use the exact checkpoint and quantization that matches your hardware and latency target.

Local runtimes: Ollama where supported, LM Studio where supported, llama.cpp where supported, Transformers

Platforms: Windows, macOS, Linux

HardwareVaries by checkpointRuntimeOllama or LM Studio where supported, llama.cpp, Transformers, vLLMContextCheck official model cardLast updated2026
Meta model page →

Related models

Llama 3 70BBuilders who want a widely supported open-weight chat model with broad runtime compatibility.Llama 4 ScoutTeams evaluating Llama-family models for multimodal assistant, long-context, and application workflows.Llama 4 MaverickBuilders comparing current Llama-family models for assistant, multimodal, and reasoning-oriented workflows.