mlsanityData to 7 Oct 2026

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

arXiv 2411.17713 ↗First posted 18 Nov 2024cs.DC cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

This paper presents Llama Guard 3-1B-INT4, a compact and efficient Llama Guard model, which has been open-sourced to the community during Meta Connect 2024. We demonstrate that Llama Guard 3-1B-INT4 can be deployed on resource-constrained devices, achieving a throughput of at least 30 tokens per second and a time-to-first-token of 2.5 seconds or less on a commodity Android mobile CPU. Notably, our experiments show that Llama Guard 3-1B-INT4 attains comparable or superior safety moderation scores to its larger counterpart, Llama Guard 3-1B, despite being approximately 7 times smaller in size (440MB).

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 8 of its 14 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

8 of 14 references.

References · 8

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  3. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  4. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  5. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  6. 2021A White Paper on Neural Network Quantizationcited by 453
  7. 2024ShortGPT: Layers in Large Language Models are More Redundant Than You Expectcited by 369
  8. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 320

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 11.

24 papers.

Sort:

By area:

  1. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 43
  2. 2025Towards Reasoning Ability of Small Language Modelscited by 29
  3. 2025ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrailscited by 29
  4. 2025WebGuard: Building a Generalizable Guardrail for Web Agentscited by 20
  5. 2025X-Guard: Multilingual Guard Agent for Content Moderationcited by 13
  6. 2025Distributional AGI Safetycited by 8
  7. 2025LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderatorscited by 7
  8. 2025Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMscited by 7
  9. 2025Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilitiescited by 5
  10. 2025A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthinesscited by 5
  11. 2025Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignmentcited by 4
  12. 2026LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrailscited by 4
12 more
  1. 2026AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attackscited by 3
  2. 2026An AI Agent Execution Environment to Safeguard User Datacited by 3
  3. 2026MobileMoE: Scaling On-Device Mixture of Expertscited by 3
  4. 2025MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulationcited by 2
  5. 2025When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Modelscited by 1
  6. 2026MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deploymentcited by 1
  7. 2026Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defensecited by 1
  8. 2026Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Modelscited by 1
  9. 2026To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMscited by 0
  10. 2026RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attackscited by 0
  11. 2026Distilling Safe LLM Systems via Soft Prompts for On Device Settingscited by 0
  12. 2026Sapien: A Stateful Policy Engine for Autonomous AI Agentscited by 0