Project Maya - run GLM-5.3-Flash (321B MoE) and DeepSeek-V4.1-Flash-1017 (748B 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.
mw00/project-maya is accelerating — star growth is speeding up by +48.1/day (97th percentile in the tracked cohort), on top of +63.7 stars/day. A recent release is helping fuel the run.
Reconstructed from 7 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 86.
Release count rose to 72.
Release count rose to 70.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/mw00/project-maya)Elevated breakout odds over the next 14 days, led by star acceleration (97th pctl) and star velocity (92th pctl). Confidence is low given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Release count rose to 65.