Liquid AI

LFM2.5-8B-A1B

A compact model for reasoning, multilingual tools, structured output, and on-device agents.

open-weightsreasoningagentsmultilingual

Model record

LFM2.5-8B-A1B model overview

LFM2.5-8B-A1B is a open weights model from Liquid AI. It was released on May 28, 2026. Its strongest case is low active size, while buyers should account for custom license.

LFM2.5-8B-A1B benchmark snapshot

EvaluationReported scoreWhat it probes
MMLU-ProNot reportedBroad knowledge and multi-step reasoning
GPQA DiamondNot reportedGraduate-level science reasoning
SWE-bench VerifiedNot reportedVerified real-repository issue resolution
LiveCodeBenchNot reportedContamination-aware competitive programming
SWE-Bench ProNot reportedLonger, harder professional software tasks
Artificial Analysis Intelligence IndexNot reportedComposite third-party capability index; version matters

Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.

LFM2.5-8B-A1B strengths

  • Low active size
  • 128K context

LFM2.5-8B-A1B limitations

  • Custom license
  • No model-specific price
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.

Source record

Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.

Source limitation: Supplemental official model card: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B

Read Liquid AI LFM2.5 announcement