modelgrep
L

LiquidAI: LFM2-24B-A2B

liquid/lfm-2-24b-a2b

165th smartest of 178Cheaper than 98% of paid
Use via OpenRouter ↗
Intelligence
10.5
165th of 178
Design Elo
Speed
53
157th fastest
Latency
210ms
first token
Input price
$0.030
7th cheapest
Context
128K

How it compares

Smarter than7%
of all ranked models
Faster than47%
of all ranked models
Cheaper than98%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis9th percentile
Intelligence Index
10.5
Coding Index
3.6
Agentic Index
3.7
GPQA Diamond
47%
Humanity's Last Exam
4%
SciCode
11%
Tau²-Bench (agentic)
11%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Together$0.030$0.120100%

Specifications

Context window128K
Max output
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

LFM2-24B-A2B FAQ

How much does LFM2-24B-A2B cost?

LFM2-24B-A2B costs $0.030 per million input tokens and $0.120 per million output tokens via OpenRouter, making it 7th cheapest of 298 paid models.

How smart is LFM2-24B-A2B?

LFM2-24B-A2B scores 10.5 on the Artificial Analysis Intelligence Index, ranking 165th of 178 benchmarked models, with a GPQA Diamond score of 47%.

How fast is LFM2-24B-A2B?

LFM2-24B-A2B generates around 53 tokens per second with 210ms time-to-first-token (p50), the 157th fastest tracked model.

What is LFM2-24B-A2B's context window?

LFM2-24B-A2B supports a 128K-token context window. It accepts text input.

Compare head-to-head