Ornith-1.0–35B: The MoE Model That Runs Like 3B, Thinks Like 27B

DeepReinforce’s Ornith-1.0–35B MoE delivers near-27B dense quality at a fraction of the compute. I tested it on llama.cpp — no upgrades…

 

​ DeepReinforce’s Ornith-1.0–35B MoE delivers near-27B dense quality at a fraction of the compute. I tested it on llama.cpp — no upgrades…Continue reading on Medium »   Read More LLM on Medium 

#AI

You May Also Like

More From Author