PulseAugur
EN
LIVE 14:38:26

Liquid AI ships tiny LFM2.5-230M for on-device agent tasks

By PulseAugur Editorial · [1 sources] ·

Liquid AI has released LFM2.5-230M, its smallest model to date, designed for on-device inference on edge hardware like phones and robots. This 230-million-parameter model excels at data extraction and tool use, outperforming larger models on specific benchmarks like IFEval and IFBench. While not suited for complex reasoning tasks such as math or coding, its small footprint and efficient architecture allow for fast inference, making it ideal for local data processing and lightweight agentic workloads. AI

IMPACT Enables more capable AI agents and data processing directly on edge devices, reducing reliance on cloud infrastructure.

RANK_REASON Release of a small, specialized model focused on on-device inference and specific tasks, rather than a frontier model release.

Read on MarkTechPost →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Liquid AI ships tiny LFM2.5-230M for on-device agent tasks

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Release of a small, specialized model focused on on-device inference and specific tasks, rather than a frontier model release.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
90 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

    <p>Liquid AI released LFM2.5-230M, its smallest model yet. The 230M-parameter, open-weight model runs on-device at 213 tok/s on a Galaxy S25 Ultra and 42 on a Raspberry Pi 5. Built on the LFM2 architecture, it targets tool use and data extraction, beating larger models like Qwen3…

RELATED ENTITIES

RELATED TOPICS