LiquidAI: LFM2-8B-A1B

Liquid AIID: liquid/lfm2-8b-a1b

LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.

Pricing per 1M Tokens

Input (Prompt)$0.01
Output (Completion)$0.02
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length33K
Max Output TokensN/A
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct TypeN/A
Top Provider Context33K
Top Provider Max OutputN/A
ModeratedNo

Compare this model

See how LiquidAI: LFM2-8B-A1B stacks up against other models.

vs LiquidAI: LFM2-24B-A2Bvs LiquidAI: LFM2.5-1.2B-Thinking (free)vs LiquidAI: LFM2.5-1.2B-Instruct (free)vs LiquidAI: LFM2-2.6B

More from Liquid AI

LiquidAI: LFM2-24B-A2B
Input$0.03
Context33K
LiquidAI: LFM2.5-1.2B-Thinking (free)
InputFree
Context33K
LiquidAI: LFM2.5-1.2B-Instruct (free)
InputFree
Context33K
LiquidAI: LFM2-2.6B
Input$0.01
Context33K

Last updated: March 23, 2026

First tracked: March 23, 2026