LFM2-24B-A2B

24B parameter Mixture-of-Experts model with 2B active parameters — our largest model for laptops and single-GPU applications

← Back to Text Models

LFM2-24B-A2B is Liquid AI’s largest Mixture-of-Experts model, combining 24B total parameters with only 2B active parameters per forward pass. This delivers the quality of much larger models with the efficiency needed for laptops and single-GPU deployments.

HFGGUFMLXONNX

Specifications

Property	Value
Parameters	24B (2B active)
Context Length	32K tokens
Architecture	LFM2 (MoE)

MoE Efficiency

24B quality, 2B inference cost

Laptop-Ready

Runs on laptops and single GPUs

Tool Calling

Native function calling support

Quick Start

Transformers

llama.cpp

vLLM

LFM2-24B-A2B requires vLLM ≥0.15.1 and transformers ≥5.1.0. Install transformers on top of the vLLM image.

Install:

uv pip install "vllm>=0.15.1"
uv pip install "transformers>=5.1.0"

Run:

from vllm import LLM, SamplingParams

llm = LLM(model="LiquidAI/LFM2-24B-A2B")

sampling_params = SamplingParams(temperature=0.1, top_k=50, repetition_penalty=1.05, max_tokens=512)

output = llm.chat("What is machine learning?", sampling_params)
print(output[0].outputs[0].text)