🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Agentic-first Cursor Rules powered by MiniMax M3 - clarify-first prompting, interleaved thinking, and full tool orchestration for production-ready AI coding
MiniMax H3 Turbo LoRA ComfyUI - minimax h3, turbo lora, comfyui custom nodes, text-to-video, image-to-video, reference-to-video, 33B omni-modal, stereo audio, H3-VisualVAE, sglang. Local 768p 4-15s, github workflow. Download:🡇
minimax-ai-provider is a community provider that use minimax-m2 to provide language model support for the AI SDK.
Quantify cli agent vibes, run experiments, look at pretty numbers
Interactive demo showcasing MiniMax-M2's interleaved thinking for agentic workflows, demonstrating adaptive strategy after each tool call with transparent traces and cost benchmarking.
Free Kimi, DeepSeek, MiniMax, GLM(soon). All-free provider in 9Router (Dahl Global) Export 9Router Backup and Import.
Patch VS Code Copilot Chat to use MiniMax API instead of Anthropic. Zero dependencies, one command.
Ready-to-use Claude Code workspaces for 20+ LLM providers: Anthropic Pro/Max, GLM Coding Plan, Kimi K2, DeepSeek, Qwen, MiniMax M2.7, Xiaomi MiMo, OpenRouter, Ollama Cloud, AWS Bedrock, Google Vertex, Azure Foundry and DGX Spark local setups.
MiniMax H3 is a general-purpose, omni-modal generative system. It supports unified understanding of multimodal contexts composed of text, images, video, and audio, and can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds.
Unofficial implementation of minimac-speech paper
To associate your repository with the minimax-m2 topic, visit your repo's landing page and select "manage topics."