Lab release history
Last updated May 28, 2026
Liquid AI model releases
MIT-spun lab building efficient Liquid Foundation Models for edge and on-device deployment. This page collects the lab's model releases, lifecycle events, source links, and model metadata in one crawlable record.
Most recent in this set
2 models
LFM2.5-8B-A1B
AvailableLiquid AI's on-device Mixture-of-Experts model: 8.3B total parameters with only ~1.5B active per forward pass (32 experts, 4 active per token). Uses Liquid's hybrid architecture — 18 double-gated LIV convolution blocks plus 6 grouped-query-attention layers — for a 131K-token context that runs in under ~6GB of memory on consumer hardware. A reasoning-only model that emits an explicit chain of thought before its answer, with strong tool-calling and agentic performance for its size. Builds on the October 2025 LFM2-8B-A1B, expanding the context window to 128K and scaling pretraining from 12T to 38T tokens. Released May 28 2026 under the LFM Open License; caught in a July catalog-gap sweep.
LFM2 1.2B
AvailableLiquid AI hybrid model for efficient CPU/GPU/NPU local deployment, using short convolutions plus attention blocks.