Liquid
LiquidAI: LFM2.5-24B-A2B
liquid/lfm-2.5-24b-a2b
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks.
Input
$0.05
/ 1M tokens
Output
$0.7
/ 1M tokens
Context window
128K
tokens
Limits
Context
128,000
tokens
Max output
8,192
6.4% of the context window
Parameters
23,971,585,280
Model facts
Author
Liquid
Tokenizer
Other
Modality
Text -> Text
License
Other
Created
Oct 13, 2026
Hugging Face
LiquidAI/LFM2.5-24B-A2B
Default generation parameters
repetition_penalty
1.05
temperature
0.1
top_k
50
Reasoning
Required
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextOutput · Text
Generation controls
Frequency penaltyInclude reasoningLogprobsMax completion tokensMax tokensMin pPresence penaltyReasoningRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobs