The Local LLM Index / Quantization & Formats / #4
mw00/project-maya
by mw00 · Quantization & Formats · updated today
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.
80
momentum
2,044
stars
262
forks
#4
rank
cudadeepseekdeepseek-v4glmglm-5llmllm-inferencelocal-llmminimaxminimax-m3mixture-of-expertsmoe
View on GitHub →