Yz

lfm2

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

Araç Kullanımı 24b
Hızlı Kurulum (Ollama kuruluysa) 
ollama run lfm2

Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.

Varyantlar

Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.

EtiketBoyutBağlamGirdiKomut
latest 14GB 32K Text ollama run lfm2:latest
24b 14GB 32K Text ollama run lfm2:24b
24b-a2b 14GB 32K Text ollama run lfm2:24b-a2b
24b-q4_K_M 14GB 32K Text ollama run lfm2:24b-q4_K_M
24b-q8_0 25GB 32K Text ollama run lfm2:24b-q8_0
24b-bf16 48GB 32K Text ollama run lfm2:24b-bf16

Model Detayları ve Benchmarklar (kaynak: ollama.com)

image.png

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

  • Best-in-class efficiency: A 24B MoE model with only 2B active parameters per token, fitting in 32 GB of RAM for deployment on consumer laptops and desktops.
  • Fast edge inference: 112 tok/s decode on AMD CPU, 293 tok/s on H100. Fits in 32B GB of RAM.
  • Predictable scaling: Quality improves log-linearly from 350M to 24B total parameters, confirming the LFM2 hybrid architecture scales reliably across nearly two orders of magnitude.

image.png