Disk-backed Local Cluster Inference Across Machines

Colibrì is a pure-C, zero-dependency inference engine that runs frontier MoE models (GLM-5.x 744B, Kimi K3 2.8T, DeepSeek V4, Qwen3.x) on consumer hardware by streaming disk-resident experts into a unified VRAM/RAM/NVMe tier hierarchy. It offers chat/serve/web front ends plus CPU, CUDA, Metal and Vulkan backends.

AI Frameworks | C · inference-engine · moe