LiquidAI: LFM2-24B-A2B

Text input Text output
Author's Description

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.

Key Specifications
Cost
$$
Context
32K
Parameters
24B
Released
Feb 25, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Presence Penalty Min P Temperature Top P Frequency Penalty Max Tokens Stop Logit Bias
Performance Summary

LiquidAI's LFM2-24B-A2B, a 24B parameter Mixture-of-Experts model with 2B active parameters, demonstrates a strong profile for efficient on-device deployment. It consistently performs among the fastest models, ranking in the 97th percentile across seven benchmarks, and offers highly competitive pricing, placing in the 89th percentile. The model also exhibits exceptional reliability with a 98% success rate, indicating minimal technical failures. In terms of specific performance, LFM2-24B-A2B excels in General Knowledge, achieving 97.5% accuracy and ranking in the top 3 for speed, making it the most accurate among models of comparable speed. It also shows strong performance in Ethics (98.0% accuracy) and Coding (71.0% accuracy). A significant strength is its speed in Email Classification, where it achieved 100th percentile speed and was the #1 fastest model, despite a lower accuracy of 86.0%. However, the model shows notable weaknesses in Instruction Following (38.0% accuracy) and Reasoning (50.0% accuracy), suggesting areas for improvement in complex multi-step tasks. Its hallucination rate, at 88.0% accuracy for identifying fictional concepts, is also an area that could be enhanced.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.03
Completion $0.12

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Together
Together | liquid/lfm-2-24b-a2b-20260224 32K $0.03 / 1M tokens $0.12 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by liquid