Models

3,545 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17

Most downloaded A–Z Recently synced

LTX 2 Pro Lightricks LTX-2 Pro is a high-fidelity text and image-to-video model with integrated upscaling and sound-read… Video · Open weights Open weights
Lucid Realism Leonardo Interactive Lucid Realism is a photoreal image model tuned for natural lighting, skin detail, and believable ma… Image · Open weights Open weights
Lyra 2.0: Explorable Generative 3D Worlds NVIDIA Lyra 2.0 is NVIDIA’s generative 3D world model for creating persistent, explorable virtual environm… Multimodal · Open weights Open weights
Lyria 3.5 Google DeepMind Lyria 3.5 is Google DeepMind's newest music generation model, launched in Google Flow Music with ad… Audio · Open weights Open weights
Magistral Medium Mistral AI Magistral Medium is Mistral’s mid-tier model in the Magistral line, designed to balance stronger re… Text · Open weights Open weights
Magistral Medium 1.2 Mistral AI Magistral Medium 1.2 is Mistral AI’s mid-tier reasoning model, designed to balance capability and e… Text · Open weights Open weights
Magistral Small 1.2 Mistral AI Magistral Small 1.2 is Mistral AI’s compact reasoning model, optimized for efficiency and cost-sens… Text · Open weights Open weights
MARC Memories.ai MARC is a 4B parameter video understanding model that uses memory augmented reinforcement learning… Video · Open weights Open weights
Megatron-Turing NLG Microsoft Megatron-Turing NLG is a 530B-parameter Transformer co-developed by NVIDIA and Microsoft. Trained o… Text · Open weights Open weights
Memories S0 Memories.ai Memories S0 is a 3B parameter video understanding model built for security and surveillance use cas… Video · Open weights Open weights
Mercury Inception Labs Mercury is Inception Labs’ diffusion large language model family built for ultra-fast, high-quality… Text · Open weights Open weights
Mercury 2.5 Inception Labs Mercury 2.5 is Inception Labs' diffusion based large language model that generates text in parallel… Text · Open weights Open weights
Meridian Viggle AI Meridian is a video to video model that regenerates existing footage from a new camera viewpoint an… Video · Open weights video to video pipeline
MiMo V2.5 Pro UltraSpeed Xiaomi MiMo-V2.5-Pro-UltraSpeed is Xiaomi MiMo’s 1T-parameter high-speed reasoning model variant built wit… Text · Open weights Open weights
MiniMam Music 1.5 MiniMax Earlier MiniMax music model enabling up to 4-minute songs with natural vocals, rich arrangements an… Audio · Open weights Open weights
MiniMax Music 1.0 MiniMax First MiniMax end-to-end music model, generating 60-second pieces with vocals and accompaniment fro… Audio · Open weights Open weights
MiniMax Music 2.0 MiniMax Next-gen MiniMax music model that creates around 5-minute, fully structured songs with expressive v… Audio · Open weights Open weights
MiniMax Music 2.5 MiniMax MiniMax Music 2.5 is an AI music model that gives paragraph-level control over song structure and d… Audio · Open weights Open weights
MiniMax Music 2.5 Plus MiniMax MiniMax Music 2.5+ adds instrumental music generation, extending beyond songs so prompts can produc… Audio · Open weights Open weights
MiniMax Speech 1.0 HD MiniMax High-definition T2A-01 speech model with hundreds of preset voices, rich emotion control and rapid… Audio · Open weights Open weights
MiniMax Speech 1.0 Turbo MiniMax Speed-focused Speech-01 variant delivering fast, natural TTS for everyday use while the HD version… Audio · Open weights Open weights
Minimax Speech 2.0 HD MiniMax High-fidelity Speech-02 model using AR Transformer plus Flow-VAE, aimed at top-tier zero-shot TTS q… Audio · Open weights Open weights
Minimax Speech 2.0 Turbo MiniMax Low-latency Speech-02 variant optimized for real-time performance, balancing speed and quality for… Audio · Open weights Open weights
MiniMax Speech 2.5 MiniMax MiniMax Speech 2.5 is a multilingual voice generation model that boosts naturalness and cloning fid… Audio · Open weights Open weights
Minimax Speech 2.6 HD MiniMax High-quality version of MiniMax Speech 2.6, focused on ultra-natural voice, Fluent LoRA cloning and… Audio · Open weights Open weights
Minimax Speech 2.6 Turbo MiniMax Turbo variant of Speech 2.6, tuned for ultra-low latency and efficiency while preserving multilingu… Audio · Open weights Open weights
Minimax Speech 2.8 HD MiniMax High-definition MiniMax TTS model focused on studio-grade, multilingual speech, rich emotion contro… Audio · Open weights Open weights
Minimax Speech 2.8 Turbo MiniMax Latency-optimized sibling of Speech-2.8-HD, trading a bit of ultimate fidelity for faster, cheaper… Audio · Open weights Open weights
MiniMax Text 01 MiniMax o3 is OpenAI’s reasoning focused model. It delivers careful step by step analysis with solid coding… Text · Open weights Open weights
Miso TTS 8B Miso Labs MisoTTS is Miso Labs’ open-weight 8B text-and-audio-conditioned speech generation model for express… Audio · Open weights Open weights
Mistral 3 14b Instruct Mistral AI Ministral 3 14B Instruct 2512 is Mistral’s largest Ministral 3 model, built as an efficient instruc… Multimodal · Open weights Open weights
Mistral 3.1 Small Mistral AI Mistral 3.1 Small is a fast, cost-efficient reasoning model with long context, reliable tool callin… Text · Open weights Open weights
Mistral Large 2 Mistral AI Mistral Large 2 is Mistral AI’s flagship open-weight dense LLM, designed for strong reasoning, codi… Text · Open weights Open weights
Mistral Moderation 2 Mistral AI Mistral Moderation 2 is Mistral’s latest moderation model with a 128k context window and built-in j… Text · Open weights Open weights
Mistral OCR 4 Mistral AI Mistral OCR 4 extracts and structures content from PDF, DOC, PPT, and OpenDocument files, returning… Multimodal · Open weights Open weights
MM1 Apple MM1 is Apple Research’s multimodal LLM blueprint: a vision encoder feeding a text decoder via cross… Text · Open weights Open weights