MiniMax Sparse Attention (MSA)

MAX is Modular’s open and extensible AI inference framework for building and serving models. It supports thousands of model architectures across image, video, speech, and text modalities, exposes OpenAI-compatible endpoints, and can program deployments across multiple GPUs, nodes, and mixed hardware. MAX is part of Modular’s unified stack alongside Mojo, the company’s Pythonic systems language for CPUs, GPUs, and ASICs; Modular describes MAX as providing portable model serving and performance across different hardware platforms.

An AI API service from MiniMax that provides access to generation capabilities and context preprocessing associated with the MiniMax-H3 language model. The API includes a 2K generation stage and a context preprocessor that are not included in MiniMax-H3's open-weight release.

MiniMind is an open-source tiny large-language-model project and end-to-end training tutorial developed by Jingyao Gong. Its main dense model is approximately 64M parameters, and the repository provides the model architecture, tokenizer, datasets, inference code, and training pipeline. The pipeline covers pretraining, supervised fine-tuning, hand-written LoRA, DPO, PPO, GRPO, CISPO, model distillation, tool calling, adaptive thinking, and agentic reinforcement learning. Core algorithms are implemented directly with native PyTorch rather than relying on high-level abstractions from third-party training libraries. Its agentic reinforcement-learning path performs multi-turn rollouts, executes generated tool calls, appends tool observations to the context, calculates trajectory-level rewards, and updates the policy; rollout can use local PyTorch generation or an SGLang server. MiniMind supports dense and mixture-of-experts variants, single- and multi-GPU training, YaRN-based RoPE length extrapolation, Transformers-format models, and inference through llama.cpp, vLLM, or Ollama. The repository also includes a Streamlit chat interface and a lightweight OpenAI-compatible API server with tool-call and reasoning fields. It is released under the Apache License 2.0.

MiniMax is an artificial-intelligence company and model provider offering large language models through hosted APIs, including models designed for coding, reasoning, and tool-using agent workflows. It is used as a model provider by agent frameworks such as Hermes Agent.

Project Maya is an open-source local inference system for running large mixture-of-experts language models on personal hardware. Created and led by Peasant Smith and co-maintained with needmorevram, it provides model-specific engines for GLM-5.3-Flash, DeepSeek-V4.1-Flash-1017, and experimental MiniMax-M3.1-Flash, with support for NVIDIA or AMD GPUs, Linux, and experimental Windows configurations. Maya places frequently used experts in GPU memory, keeps additional experts in RAM, and reads the remainder from an NVMe SSD, moving them as inference proceeds. Its setup measures the available GPUs, CPU, RAM, and storage and tunes the configuration; layers can be split across multiple GPUs, and optional drafter, quantization, vision, KV-cache streaming, and conversation-checkpoint features are selected according to the model and hardware. The project includes a browser chat interface and hardware monitor, an OpenAI-compatible API, an Anthropic-compatible API, tool calls, image inputs, thinking-level controls, concurrent requests, and a Responses API with streaming and function-tool support. It is free and distributed under the MIT License; the repository notes that some optional model components have separate licenses or non-commercial restrictions.