Liquid AI Releases 2.6B On-Device Agent Model LFM2.5

Liquid AI released LFM2.5-2.6B, a new on-device agent model with only 2.69B parameters, capable of fully local multi-step planning, tool calling, and reasoning on phones, laptops, and robots, ensuring data never leaves the device and near-zero marginal cost per run. Official data shows 30 tok/s on mobile, and benchmarks surpass several larger models, quickly topping Hugging Face trending. Developer @nicodotdev built a fully autonomous research agent in-browser, validating the feasibility of complex agent tasks on-device with small models. This offers a cost-effective solution for mobile and offline AI applications.

Confirmed

Specs: 2.69B parameters, 34T training tokens, 128K context. Compatible with llama.cpp and GGUF at launch; MLX version optimized for Apple Silicon, supporting text generation and multilingual (Chinese, English, French, German, Arabic).
Core strengths: Dense mixture architecture, fully local multi-step planning and tool calling, zero marginal cost, suitable for simple high-throughput tasks. Official data via @BTALabs: 30 tok/s on mobile.
Benchmarks: Surpasses several larger models; topped Hugging Face trending after release.

Why it matters

On-device agent potential: Developer @nicodotdev built a fully in-browser research agent that plans, calls tools, checks results, and loops until completion, proving small models can handle complex agent tasks on-device.
Lower deployment barrier: Brings powerful tool-calling to edge devices, offering a cost-effective solution for mobile and offline AI.

2026-08-04 ~ 2026-08-06 · 18 related posts

Full story(3 episodes)→

Episode 1: Liquid AI Releases 2.6B On-Device Agent Model LFM2.5(2026-08-04, 18 posts)
Episode 2: Liquid AI 2.6B Model Matches DeepSeek in Tool Calling, 3.7x Faster(2026-08-06, 3 posts)
Episode 3: Liquid AI Releases Open-Source Edge Model LFM 2.5(2026-08-09, 4 posts)

Primary sources

Liquid AI Releases 2.6B Model: 30 tok/s on Phone with 128K Context — BTA_Labs · 2026-08-05 05:15 (UTC+08:00)
Liquid AI Launches LFM2.5-2.6B: On-Device Agentic Model Outperforming Larger Counterparts — maximelabonne · 2026-08-04 22:05 (UTC+08:00)
Liquid AI's 2.6B model powers a fully in-browser research agent — nicodotdev · 2026-08-04 22:40 (UTC+08:00)

LiquidAI Releases LFM2.5-2.6B-MLX for Edge Devices — LiquidAI · 2026-08-03
[source] Liquid AI Launches LFM2.5-2.6B: On-Device Agentic Model Outperforming Larger Counterparts — maximelabonne · 2026-08-04
Liquid AI Launches LFM2.5-2.6B: An On-Device Agentic Model Outperforming Larger Peers — helloiamleonie · 2026-08-04
[source] Liquid AI's 2.6B model powers a fully in-browser research agent — nicodotdev · 2026-08-04
LiquidAI Releases LFM2.5-2.6B Edge Model — LiquidAI · 2026-08-05
Liquid AI Releases LFM2.5-2.6B with Focus on Agentic Capabilities — Alarming_Positive_59 · 2026-08-05
Liquid AI Launches On-Device Agentic Model LFM2.5-2.6B — helloiamleonie · 2026-08-05
[source] Liquid AI Releases 2.6B Model: 30 tok/s on Phone with 128K Context — BTA_Labs · 2026-08-05
LiquidAI Releases LFM2.5-2.6B GGUF Model for Local Deployment — LiquidAI · 2026-08-05
Running Local Agents with LFM2.5-2.6B: A Step-by-Step Guide — JosephJacks_ · 2026-08-06

8 near-duplicate retellings: JosephJacks_ · alexcovo_eth · helloiamleonie · Teknium · JosephJacks_ · JosephJacks_ · JosephJacks_ · LiquidAI