Lowest-Latency LiquidAI Models

Quick answer · Updated June 2026

LFM2-24B-A2B has the lowest latency of any LiquidAI model, responding in about 182ms to first token. LFM2.5-1.2B-Instruct (free) (265ms) and LFM2.5-1.2B-Thinking (free) (331ms) round out the top three.

182msLatency

10.5Intelligence

63 t/sSpeed

$0.030Input /M

128KContext

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 LiquidAI model has the lowest latency?

What's a good alternative to LFM2-24B-A2B?

LFM2.5-1.2B-Instruct (free) (265ms) is the closest alternative on this metric, followed by LFM2.5-1.2B-Thinking (free) (331ms). See the full ranking above for the tradeoffs.

How many LiquidAI models are there?

modelgrep tracks 3 LiquidAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by LFM2-24B-A2B. 3 of them qualify for this ranking.

More LiquidAI rankings

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

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