Fastest LiquidAI Models

Quick answer · Updated June 2026

The fastest LiquidAI model is LFM2.5-1.2B-Instruct (free) at 67 output tokens per second. LFM2-24B-A2B (60 t/s) and LFM2.5-1.2B-Thinking (free) (31 t/s) round out the top three.

67 t/sSpeed

8.0Intelligence

FreeInput /M

33KContext

AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.

Frequently asked

What is the fastest LiquidAI model?

The fastest LiquidAI model is LFM2.5-1.2B-Instruct (free) at 67 output tokens per second. LFM2-24B-A2B (60 t/s) and LFM2.5-1.2B-Thinking (free) (31 t/s) round out the top three.

What's a good alternative to LFM2.5-1.2B-Instruct (free)?

LFM2-24B-A2B (60 t/s) is the closest alternative on this metric, followed by LFM2.5-1.2B-Thinking (free) (31 t/s). 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: Lowest-Latency 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 Lowest-Latency LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Best Open-Source LLMs Longest-Context LLMs