MiniMax M3.1 released on Hugging Face

MiniMax released MiniMax-M3.1-Flash on Hugging Face under its MiniMaxAI organization, an image-text-to-text model listed at 220B parameters and updated about three hours before the listing was viewed. The model page showed 357 downloads and 120 likes at the time, with inference available through the platform. The release gives developers a new multimodal large model to run or fine-tune via Hugging Face tooling.

Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up Edit Models filters Showing models from MiniMax Main Tasks Libraries Languages Licenses Other Tasks Text Generation Any-to-Any Image-Text-to-Text Image-to-Text Image-to-Image Text-to-Image Text-to-Video Text-to-Speech + 44 Parameters Reset Parameters < 1B 6B 12B 32B 128B 500B < 1B 500B Libraries PyTorch TensorFlow JAX Transformers Diffusers GGUF MLX Transformers.js Safetensors + 46 + 48 + 45 Apps vLLM llama.cpp MLX LM LM Studio Ollama Jan Draw Things DiffusionBee JoyFusion + 8 + 10 Inference Providers Groq Novita Cerebras Nscale fal Together AI Fireworks Featherless AI Zai + 9 + 11 + 10 Hardware Add your hardware Apply filters Models 1 Base only Inference Available Inference Edit filters Sort: Trending Active filters: MiniMaxAI Clear all MiniMaxAI/MiniMax-M3.1-Flash Image-Text-to-Text • 220B • Updated about 3 hours ago • 357 • 120