TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

LFM2.5 1.2B

LFM2.5-1.2B is part of Liquid AI’s on-device LFM2.5 family. The 1.2B Instruct checkpoint is optimized for conversational use, tool calling and light multimodal work, delivering high-quality responses at roughly 239 tokens per second on desktop CPUs and around 82 tokens per second on mobile NPUs, with support for llama.cpp, MLX, vLLM and quantized GGUF deployments for phones and laptops.
New Text Gen 7
Released: January 5, 2026

Overview

LFM2.5-1.2B is Liquid AI’s 1.2B hybrid edge model for on-device chat and tools, trained on 28T tokens and RL, running under 1 GB of RAM while rivaling much larger LLMs on reasoning and agentic tasks.

About Liquid AI

Liquid AI is an MIT spin-off building efficient general-purpose AI models (Liquid Foundation Models, or LFMs) that run on edge devices with less memory and power.
They recently raised $250M in Series A funding to scale model development and deployment.

Website: liquid.ai
View Company Profile

Tools using LFM2.5 1.2B

No tools found for this model yet.

Last updated: February 3, 2026
0 AIs selected
Clear selection
#
Name
Task