deepseek-v4.1POST

Project Maya: private deployment of DeepSeek V4.1 Flash and GLM-5.3-Flash on 1–16 GPUs

The open-source Project Maya runs DeepSeek V4.1 Flash-1017 (748B MoE) privately on 1 to 16 NVIDIA or AMD GPUs across Linux and Windows, with an OpenAI-compatible server and dashboard.

Nicolas Krassas

@DinosnArchived 7 days agoOriginally posted 2026.10.24

Nicolas Krassas @DinosnOriginally posted 2026.10.24

Open original on X

mw00/project-maya: 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 A... https://github.com/mw00/project-maya

x.com/dinosn/status/2113835778677858663Archived 2026.10.24 12:06