Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
Hoist tracks this board by himself every day. MixinVisuals builds the same kind of AI helper for small businesses: scheduling, inboxes, inventory and invoices, built around how your shop already runs.