Liquid AI: LFM2.5-2.6B
This model is no longer available.Add AI to your application with Puter.js.
Explore Other ModelsModel Card
LFM2.5-2.6B is a dense on-device agentic model from Liquid AI, pre-trained on roughly 34 trillion tokens with a 128K context window and native tool calling built for running inside agent harnesses.
It leads on instruction-following and tool-use benchmarks among models its size, scoring 59.17 on IFBench and 77.83 on ToolSandbox versus Qwen3.5-9B's 56.47 and 76.44. It trails Qwen3.5-9B on BFCLv4 (56.88 vs. 60.13) and AIME25 math reasoning (51.87 vs. 56.07), despite Qwen3.5-9B being more than 3x larger.
Liquid AI recommends it for high-volume agentic workloads, tool use, data extraction, RAG, and long-context tasks on edge devices, and advises against using it for agentic coding or knowledge-heavy work. For API callers, it's a solid choice when fast tool-calling and instruction following matter more than raw coding or general knowledge depth.
Context Window 128K
tokens
Max Output 8K
tokens
Input Cost $0.35
per million tokens
Output Cost $0.5
per million tokens
Input text
modalities
Tool Use Yes
Release Date Aug 11, 2026
Code Example
Add AI to your app with the Puter.js AI API, no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From Liquid AI
LFM3-1.7B
LFM3-1.7B is a text model from Liquid AI with a 256K-token context window, built for local agents and specialized applications. It is the base of the LFM3 family released on October 27, 2026. Liquid AI reports that it outperforms LFM2.5-2.6B with 35% fewer parameters. It scores 96.66 on IFEval, 71.39 on BFCL V4 and 80.36 on ToolSandbox, the highest among the models compared, and beats Qwen3.5-9B on WebArena-Verified (38.42 vs. 28.94). It trails Qwen3.5-9B on GPQA Diamond (63.37 vs. 80.40) and RULER 128K (65.56 vs. 87.11). It suits tool-calling agents, instruction-following tasks and high-volume workloads. Larger models are a better fit for knowledge-heavy or agentic coding work.
ChatLFM2.5-24B-A2B
LFM2.5-24B-A2B is a sparse Mixture-of-Experts reasoning model from Liquid AI with 24B total parameters and about 2.45B active per token. It has a 131K context window and always produces a reasoning trace before answering. It is built for agents and tool calling. Liquid AI reports IFEval 96.75, IFBench 74.69, BFCLv4 65.01, ToolSandbox 80.71 and SWE-Bench Verified 51.00. It scores higher than Qwen3.6-35B-A3B and Gemma-4-26B-A4B-it on most agentic and instruction-following tests, but trails Qwen3.6-35B-A3B on coding (SWE-Bench Verified 66.20) and GPQA Diamond (83.69 vs. 74.42). It suits developers building tool-calling agents, especially with retrieval or web search. Liquid AI advises against using it alone for knowledge-heavy tasks or where direct, non-reasoning replies are needed.
Frequently Asked Questions
LFM2.5-2.6B is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.35 |
| Output | $0.5 |
LFM2.5-2.6B was created by Liquid AI and released on Aug 11, 2026.
LFM2.5-2.6B supports a context window of 128K tokens. For reference, that is roughly equivalent to 256 pages of text.
LFM2.5-2.6B can generate up to 8K tokens in a single response.
LFM2.5-2.6B accepts the following input types: text. It produces: text.
Yes, LFM2.5-2.6B supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the LFM2.5-2.6B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials