LiquidAI: LFM2-24B-A2B

liquid/lfm-2-24b-a2b

Streaming

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per...

Pricing

Input

$0.03 / 1M

Output

$0.12 / 1M

Specs

Context

128,000 tokens

Input

text

Output

text

Released: 2026-02

Supported parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltystoptemperaturetop_ktop_p

Open weights · HuggingFace

19,169 downloads/mo

330 likes

other text-generation

arXiv:2511.23404

View on HuggingFace →

Use this model →