LFM2 24B A2B

Liquid InferenceMCP Tool Call

liquid/lfm2-24b-a2bOpen Weights

Efficient open Liquid MoE instruct model for on-device chat and tool calling

Benchmark Pricing$0.03 / 1M in$0.12 / 1M out$0.03 cache read

Context: 32,768 tokens•Max Output: 32,768 tokens•Released: 2026-02-24

TECHNICAL SPECIFICATIONS

Context Window32,76832.8K tokens

Max Output32,76832.8K tokens

LicenseLFM Open License v1.0Self-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ LFM2 24B A2B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 32,768 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling LFM2 24B A2B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.LIQUID_API_KEY,
});

const response = await client.chat.completions.create({
  model: "liquid/lfm2-24b-a2b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);