Sobre
LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.
Modelos Relacionados
Preços
Entrada
$0.01
por 1M tokens
Saída
$0.02
por 1M tokens
Combinado
$0.01
por 1M tokens
Mais barato que 92% dos modelos. Preço mediano é $0.54/1M tokens.
Calculadora de Custo
Tokens por dia1M
100K100M
Diário
$0.01
Mensal
$0.38
vs. Modelos Similares
Granite 3.3 8B (Non-reasoning)Q:0.0
$0.09+580%
Command-R (Mar '24)Q:+0.3
$0.75+5900%
Mistral 7B InstructQ:+0.3
$0.21+1548%
Qwen3 1.7B (Non-reasoning)Q:-0.3
$0.19+1404%
Desempenho
Janela de Contexto
33K
tokens
Maior que 7% dos modelos
Comparação de Janela de Contexto
Mistral: Saba
33KIgual
Qwen2.5 Coder 7B Instruct
33KIgual
Mixtral 8x7B Instruct
33KIgual
Benchmarks
MMLU-Pro
50.5%
GPQA Diamond
34.4%
HLE
4.9%
LiveCodeBench
15.1%
SciCode
6.8%
TerminalBench Hard
0.0%
MATH-500Não avaliado
AIMENão avaliado
AIME 2025
25.3%
IFBench
26.3%
Long Context Recall
0.0%
Tau2
10.5%
Média do MercadoMelhor Score