LFM2 8B A1B

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released October 2025128K context≈ 96,000 words8B params

LFM2 8B A1B is a compact model built on LiquidAI's hybrid recurrent-attention architecture, which gives it an unusual memory efficiency compared to standard transformers of similar size. It handles text tasks with a lean footprint, making it practical for constrained environments. The non-standard architecture means tooling support may lag behind more conventional models.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Multimodal

Moderate

Creative Writing

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

LFM2 8B A1B

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released October 2025128K context≈ 96,000 words8B params

LFM2 8B A1B is a compact model built on LiquidAI's hybrid recurrent-attention architecture, which gives it an unusual memory efficiency compared to standard transformers of similar size. It handles text tasks with a lean footprint, making it practical for constrained environments. The non-standard architecture means tooling support may lag behind more conventional models.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Multimodal

Moderate

Creative Writing

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Glossary

ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.AttentionA mechanism that lets the model focus on relevant parts of the input when generating each output token.Compact ModelA smaller language model designed to use fewer computational resources while still performing useful tasks.Memory EfficiencyHow well a model uses available RAM or GPU memory, allowing it to run on smaller or less expensive hardware.Recurrent-Attention ArchitectureA hybrid neural network design that combines recurrent processing (which maintains memory across sequences) with attention mechanisms, enabling better memory efficiency than standard transformers.