Liquid AI releases LFM2.5-24B-A2B: 24B params, 2B active, built for local agents
JosephJacks_ · x · 2026-10-14
Liquid AI released LFM2.5-24B-A2B, the largest member of its LFM2.5 family, designed to run locally on laptops/PCs and power multi-step tasks inside popular agent harnesses.
- 24B total parameters with only 2B active per token; reasoning at MoE speed
- Context expanded to 131K tokens; 128K-token vocabulary; pretrained on 33T tokens
- Competitive with Qwen3.6-35B-A3B (a model with 50% more total and active params) on agentic and tool-use tasks
- 184 tok/s inference on an Apple M5 Max
- Open base and post-trained weights on Hugging Face; easy to fine-tune
The company positions it as the model that makes "AI PCs" real, targeting always-on agents.
Related event: LiquidAI Releases LFM2.5-24B-A2B On-Device MoE Model(4 posts)→
More from Infra
- Ayar Labs, Wiwynn and GUC demo integrated optical compute system with live telemetry at OCP — bookwormengr · 2026-10-14
- Gavin Baker concedes some AI deals were fake, cites $1.4T commitments talking point — GavinSBaker · 2026-10-14
- Argon pushes Gemma past 120k tokens/sec on a single A100 with vLLM, a 2.9x speedup — osanseviero · 2026-10-14
- Espresso now auto-optimizes Databricks Spark jobs and configs — mattturck · 2026-10-14
- Intel Diamond Rapids motherboard shown off: 16 DDR5 slots, MRDIMM at 12800MT/s — firstadopter · 2026-10-14
- SayGM claims 70% cheaper LLM gateway with $5M ARR and crypto referral rewards — markjeffrey · 2026-10-14