On-Device & Local InferenceLiquid AI
Liquid AI publishes the LFM2 technical report
Published the LFM2 technical report — expanded to a 350M–8.3B family (dense 350M, 700M, 1.2B, 2.6B; MoE 8.3B total / 1.5B active), pretrained on 10–12T tokens, 32K context. Describes the design as coming from a hardware-in-the-loop architecture search under edge latency and memory constraints. LFM2-2.6B scored 79.56% on IFEval and 82.41% on GSM8K
Why it matters
A follow-up document to the July release. A case of an on-device family having public documentation at the level of a technical report
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2511.23404Added in Week 36, 2026 · See that week