RayCodes_LFM-2.5-A2B
Liquid AI's New LFM 2.5 Is INSANE — 184 TOK/S With Only 2B Active! (Live Tests) - High-performance local edge reasoning guide, prompts, and deployment for LFM2.5-24B-A2B hybrid architecture
- 4
- 5 wk ago
Liquid AI's New LFM 2.5 Is INSANE — 184 TOK/S With Only 2B Active! (Live Tests) - High-performance local edge reasoning guide, prompts, and deployment for LFM2.5-24B-A2B hybrid architecture
LFM 2.5: I Ran 230M AI Model on My CPU! (Liquid AI's QAD Update) - Offline AI career planner using 230M LFM2.5 model locally with Ollama.