richardyoung/ lfm2.5-24b-a2b

42 yesterday

LiquidAI LFM2.5-24B-A2B: 24B reasoning MoE with only 2.45B active. Fast agents and tool use, 16 languages.

7 models

lfm2.5-24b-a2b:latest
bbe32261d7a2 • 15GB • 128K context window •
Text input • yesterday
lfm2.5-24b-a2b:IQ3_M
979b33794199 • 11GB • 128K context window •
Text input • yesterday
lfm2.5-24b-a2b:Q4_K_M
bbe32261d7a2 • 15GB • 128K context window •
Text input • yesterday
lfm2.5-24b-a2b:Q5_K_M
1e486cf1521d • 17GB • 128K context window •
Text input • yesterday
lfm2.5-24b-a2b:Q6_K
968a01b2752d • 20GB • 128K context window •
Text input • yesterday
lfm2.5-24b-a2b:Q8_0
400b65138d8b • 25GB • 128K context window •
Text input • yesterday
lfm2.5-24b-a2b:IQ4_XS
298dabe98d01 • 13GB • 128K context window •
Text input • yesterday