Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits

RCEpic

mw00/project-maya

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B 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.

Owner: mw00 (personal account)
Stars: Stars: 2,446
Forks: Forks: 335
Language: Cuda
License: MIT
Created: 2026
Topics: cudaglmglm-5llmllm-inferencelocal-llmmixture-of-expertsmoeopenai-apiquantization
Tier: RC (2,000 to 4,999 ★) What this tier means

View on GitHub

Nearby in Cuda

All Cuda repos

Tony-Tan/CUDA_FreshmanStars: 2,813CudaRC
mirage-project/mirageStars: 2,592CudaRC
NVIDIA/CUDALibrarySamplesStars: 2,543CudaRC
rapidsai/cugraphStars: 2,253CudaRC
brucefan1983/CUDA-ProgrammingStars: 2,104CudaRC
CannyLab/tsne-cudaStars: 1,957CudaBeta