Local Ai
model page: https://ollama.com/library/minimax-m2.7
MiniMax-M1 is a large-scale open-weight reasoning model developed by MiniMax, featuring a hybrid Mixture-of-Experts (MoE) architecture with 456 billion total parameters (activating 45.9 billion per to
MiniMax-M1 is a large-scale open-weight reasoning model developed by MiniMax, featuring a hybrid Mixture-of-Experts (MoE) architecture with 456 billion total parameters (activating 45.9 billion per token). The model is designed for long-context reasoning tasks and supports up to 1 million tokens of context length. It is available through Ollama's model library for local deployment and inference.
Related
- glm 5.1 is doing well
- MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization
- Mac mini M4 48GB
- b8750
- b8753
- b8757
Source: Ollama (X) | 2026-04-12