Liquid AI reveals 8B-A1B MoE trained on 38T
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
New MoE model from Liquid AI, relevant to AI trends.
Liquid AI released LFM2.5-8B-A1B, an edge MoE model trained on 38T tokens with a 128K context window and reasoning-only chain-of-thought, featuring a doubled 128K vocabulary for non-Latin scripts and targeted RL to mitigate doom loops and hallucinations. Available on Hugging Face, it targets reliable tool calling on consumer hardware, building on the predecessor's 12T training and 32K context.
- Evaluate LFM2.5-8B-A1B for local agentic tool-use workloads, leveraging its 128K context and reasoning-only design.
For a Solutions Architect focused on AI agent orchestration and edge deployment, this model enables running capable reasoning and tool-use agents locally without cloud dependency, with long context and reduced hallucination.