LFM2 8B A1B

Name: LFM2 8B A1B
Author: Liquid AI

Liquid AIOpen WeightsPending Human Review

LFM2 8B A1B is Liquid AI’s first on-device mixture-of-experts model in the LFM2 generation. It combines the family’s short-convolution and attention blocks with sparse expert activation, totaling about 8.3B parameters and activating approximately 1.5B per token despite the A1B product name. The release includes downloadable weights and CPU-focused inference optimization, with 32K context. It targets multilingual conversation and private edge deployment. Custom Liquid licensing permits some commercial uses but requires separate licensing for larger companies.

2025-10-07

8.3B total, approximately 1.5B active

Hybrid short-convolution, attention, and Mixture of Experts

Liquid Open Model License 1.0

Compare with other models

Specifications

Parameters: 8.3B total, approximately 1.5B active
Architecture: Hybrid short-convolution, attention, and Mixture of Experts
License: Liquid Open Model License 1.0
Context Window: 32,768 tokens
Type: text
Modalities: text

Benchmark Scores

Advanced Specifications

Model Family: LFM
API Access: Not Available
Chat Interface: Not Available
Multilingual Support: Yes
Variants: LFM2-8B-A1B

Capabilities & Limitations

Capabilities: language generationefficient local inferencemultilingual
Known Limitations: Custom commercial license conditions applyFull weight memory exceeds active parameter countSmall model knowledge and reasoning are limited
Notable Use Cases: local assistantsedge applicationsprivate customization

Resources

Related Models

LFM2.5 VL 3B

Liquid AI

Liquid’s larger LFM2.5 vision model integrates a 400M SigLIP2 NaFlex encoder with the 2.6B language backbone. It strengthens screen understanding, grounding, multi-image processing, and function calling. The post-trained model answers directly without long reasoning traces, making it suitable for interactive visual assistants. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.

LFM2.5 2.6B

Liquid AI

This dense agent model scales pretraining to about 34T tokens and adds a dedicated 128K context-extension phase. Post-training combines teacher specialization, on-policy distillation, and reinforcement learning for planning and chained tool calls. The model is designed for smartphones, CPUs, and GPU serving, with downloadable base and post-trained checkpoints. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.

LFM2.5 230M

Liquid AI

Liquid’s smallest LFM2.5 text tier is designed for inexpensive local inference and downstream fine-tuning. Its training includes 19T tokens and a 32K context extension, followed by distillation, preference optimization, and reinforcement learning. It can select tools from natural-language instructions, but demonstrations of robot control rely on external low-level skills. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.