Official ornith-ai Q4_K_M GGUF (~22 GB). Multimodal 35B MoE with ~3B active; llama-server fetches weights and mmproj on first load.
Official ornith-ai Q4_K_M GGUF (~22 GB). Multimodal 35B MoE with ~3B active; llama-server fetches weights and mmproj on first load.