Lowest-Latency LLMs

Quick answer · Updated June 2026

Llama Guard 4 12B has the lowest latency of any LLM, responding in about 118ms to first token. Phi 4 Mini Instruct (140ms) and Llama 3.1 8B Instruct (141ms) round out the top three.

118msLatency

18 t/sSpeed

$0.180Input /M

164KContext

AI models ranked by time-to-first-token (p50). The most responsive large language models for real-time and interactive use cases.

Frequently asked

Which LLM has the lowest latency?

Llama Guard 4 12B has the lowest latency of any LLM, responding in about 118ms to first token. Phi 4 Mini Instruct (140ms) and Llama 3.1 8B Instruct (141ms) round out the top three.

What's a good alternative to Llama Guard 4 12B?

Phi 4 Mini Instruct (140ms) is the closest alternative on this metric, followed by Llama 3.1 8B Instruct (141ms). See the full ranking above for the tradeoffs.

By maker

OpenAI Qwen Google Mistral Anthropic Meta DeepSeek NVIDIA

All rankings

Small & Fast LLMs Smartest LLMs Best LLMs for Coding Best LLMs for Design & Frontend Fastest LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Best Open-Source LLMs Longest-Context LLMs