LFM2.5-24B-A2B: Built for fast on-device agents
It is designed for fast, private agents that run entirely on device, with a reasoning‑only architecture that outputs a chain of thought before the final answer.
Key points
- It outperforms Qwen3.6‑35B‑A3B on 5 of 8 agentic benchmarks, scoring 48.09 on LiveClaw versus 38.19.
It scored 48.09 on LiveClaw versus 38.19 for the competitor, and 27.69 on AutomationBench versus 8.72.
Both the base and post‑trained versions are open‑weight and available today on Hugging Face and Liquid Console. The model supports llama.cpp, MLX, vLLM, SGLang, and ONNX, enabling edge inference on Apple, AMD, Qualcomm, and Nvidia hardware.
The story so far
7 episodes →- LFM2.5-24B-A2B: Built for fast on-device agentsthis story
LFM2.5-24B-A2B: Built for fast on-device agents
liquid.ai · 14 October 2026-oOdUn61bDRSykk4H951SoDOHzqoOe1.png)
Loading the full article…
This text was published by liquid.ai and written by Liquid AI. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
1source- Hacker News discussion · 49 pointsnews.ycombinator.com
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Google launches Gemini 4 Argon model globally for Pro and Ultra subscribers with introductory API pricing · 25 src
- Simon Willison prompts Claude Opus 5.5 Max to build a Three.js web game · 1 src
- Developer uses Claude to write 180K-line compatibility layer in 3 weeks · 1 src
- Meta introduces Muse Wonder and Muse Wonder Full frontier models for agents · 27 src
- Anthropic may launch Opus 6 next week to rival OpenAI’s Bell · 2 src
Comments
via GitHub Discussions