LFM2.5-24B-A2B
LFM2.5-24B-A2B is a 24B reasoning model with 2B active parameters.
What the release provides
Liquid describes it as the final and largest LFM2.5 release. It always reasons before answering and has a 131,072-token checkpoint context.LFM2.5-24B-A2B official model card
How to use it well
Practical guidance. Plan memory from the full checkpoint and context cache. Compare task completion with reasoning length and response time. For local agents, validate the actual tool calls and resulting state rather than treating a long explanation as evidence of successful work.
Hosted API contract
The API catalog lists lfm2.5-24b-a2b with a 128,000-token window. Its supported inputs and limits can differ from the downloadable checkpoint.Liquid API model catalog
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API, Downloadable |
| Model identifiers | LiquidAI/LFM2.5-24B-A2Blfm2.5-24b-a2b |
| Context window | 131,072 tokens Downloadable checkpoint limit; the hosted API has a separate service contract. LFM2.5-24B-A2B official model card |