llama-tierkv
llama.cpp fork that lets a 27B coding agent run on a 16GB GPU: the KV cache lives on a three-tier desk/bookshelf/archive (VRAM window / host RAM / SSD) with attention-driven page recall, so context reaches 256K without decode slowing down.
An independent fork of llama.cpp for running end-to-end coding-agent tasks on consumer GPUs with limited VRAM.
⚡ How to use llama-tierkv
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/arczhi-llama-tierkvCapabilities
Do you own llama-tierkv?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.