Liquid AI Releases LFM2.5-24B-A2B, a Sparse 24B Model That Outperforms Larger Competitors on Agent Tasks
Sign in✓ Signed in
Liquid AI has released LFM2.5-24B-A2B, a 24-billion-parameter mixture-of-experts model with only 2.45 billion parameters active per token, positioned to challenge larger competitors in on-device agentic workloads. Published on October 13, 2026, as open-weight checkpoints on Hugging Face, the model represents the largest member of Liquid's LFM2.5 family and signals a strategic shift toward reasoning-focused, locally-deployable agents.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...