LFM2.5-8B-A1B — AI Model Review & Pricing

by Liquid AI Intelligent Open Weight Rank #96 of 124

Liquid AI releases LFM2.5-8B-A1B, an on-device mixture-of-experts model with 8B total parameters and 1B active, trained on 38T tokens with RL post-training. Optimized for fast tool calling and instruction following on consumer hardware with a 128K context window.

Choose a model to compare against LFM2.5-8B-A1B

Specifications

Specifications for LFM2.5-8B-A1B
AttributeValue
Lab Liquid AI
Tags Intelligent Open Weight
Release Date 2026-05
Context Window 128,000 tokens
Input Price / 1M $0.00
Output Price / 1M $0.00
Input Modalities Text
Output Modalities Text

Strengths

  • Extremely efficient on-device inference with only 1B active parameters
  • Strong tool calling and instruction following (IFEval 91.84, BFCLv3 64.36)
  • Doubled vocabulary (128K) with significant multilingual tokenization improvements
  • Day-one support for llama.cpp, MLX, vLLM, and SGLang
  • Competitive with much larger dense and MoE models on agentic tasks

Weaknesses

  • Limited reasoning depth (AIME25: 42.53) compared to frontier models
  • Small active parameter count limits complex multi-step reasoning
  • Not yet available on major API providers like OpenRouter

Best For

  • On-device AI assistants and personal agents
  • Tool-calling workflows on consumer hardware
  • Multilingual applications with non-Latin scripts
  • Edge deployment where latency and efficiency matter most

In Depth: LFM2.5-8B-A1B

Summary

LFM2.5-8B-A1B is an AI model from Liquid AI ranked #96 of 124 on the LMRank leaderboard.

Released 2026-05. It currently appears in the Overall category on LMRank and 1 other category. It supports Text input and produces Text output, with a context window of 128,000 tokens. Input pricing is $0.00 per 1M tokens and output is $0.00 per 1M tokens on OpenRouter.

Sources & Further Reading

Related Models