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

PaperBanana dwzhu-pku PaperBanana is an agentic framework that turns raw scientific content into publication-ready method… Multimodal · Open weights Open weights
Parcae Sandy Research Parcae is a Sandy Research model family described as "a family of stable looped models." The public… Text · Open weights Open weights
Parse 5 Cohere A 2.3B parameter vision language model that converts enterprise documents such as PDFs, PPTs and JP… Multimodal · Open weights Open weights
Perceptron Mk1 Perceptron AI Perceptron Mk1 is Perceptron’s closed-source vision-language model for video understanding, image r… Multimodal · Open weights Open weights
Persimmon Humans& Persimmon is a research-preview user model from humans& that simulates realistic human behavior in… Text · Open weights Open weights
PersonaLive GVC Lab PersonaLive is a real-time diffusion model for expressive portrait image animation in live streamin… Multimodal · Open weights image to video pipeline
Phi 3.5 MoE Gentext Group Phi-3.5-MoE is Microsoft’s open-weight Mixture-of-Experts model (16×3.8B, ~6.6B active) built for s… Text · Open weights Open weights
Phi 4 reasoning Microsoft Phi-4-reasoning is an open-weight model fine-tuned from Phi-4 with chain-of-thought SFT and reinfor… Text · Open weights Open weights
Phi Silica Microsoft Phi Silica is Microsoft’s on-device small language model (~3.3B params) built to run locally on Cop… Text · Open weights Open weights
Phonon Gradium Phonon is Gradium’s private-beta 100M-parameter on-device text-to-speech model for low-latency, off… Video · Open weights Open weights
Photon Moondream Photon is Moondream’s real-time vision-language model aimed at production video and image analysis.… Multimodal · Open weights Open weights
Photon 1 Flash Luma 1 Photon Flash is the speed-tuned variant. It trades a bit of peak detail for much lower latency wh… Text · Open weights Open weights
Piper Nabu Casa Piper is a fast local neural text-to-speech engine built on VITS and exported to ONNX, designed to… Audio · Open weights Open weights
Pocket TTS Spokenword danneauxs Pocket-TTS-Spokenword is an enhanced version of Kyutai’s Pocket TTS built for emotionally expressiv… Audio · Open weights Open weights
Pokee Isaac 28B Pokee AI Pokee Isaac 28B is a 28 billion parameter agentic language model built for tool use and long horizo… Text · Open weights Open weights
Project Eden JetBrains Project Eden is VAST AI Research / Tripo’s research-preview world model for persistent multiplayer… Multimodal · Open weights Open weights
Quasar 438B Multiverse Computing Quasar 438B is a 438 billion parameter text only large language model built for reasoning. Extended… Text · Open weights Open weights
Qwen 2.5 Alibaba Qwen 2.5–72B is Alibaba’s flagship open-weight 72B dense LLM for high-accuracy reasoning, coding, a… Text · Open weights Open weights
Qwen 2.5 Max Alibaba AI model by Alibaba Text · Open weights Open weights
Qwen 2.5 Plus Alibaba Qwen 2.5 Plus is the balanced tier that trades a bit of speed for higher accuracy and stronger codi… Text · Open weights Open weights
Qwen 2.5 Turbo Alibaba Qwen 2.5 Turbo is the low-latency tier for high-throughput apps. It offers solid reasoning and codi… Text · Open weights Open weights
Qwen 3 Alibaba Qwen 3 is Alibaba’s flagship general model for strong reasoning, coding, and multilingual use. It s… Text · Open weights Open weights
Qwen 3 Max Alibaba Qwen3-Max is Alibaba’s flagship Qwen3 model for high-accuracy reasoning, coding, and multilingual t… Text · Open weights Open weights
Qwen 3 Omni Flash Alibaba Qwen 3 Coder Flash is the speed-tuned coding variant. It reads repos, writes diffs and tests, and s… Text · Open weights Open weights
Qwen 3.5 Flash Alibaba Qwen3.5-Flash is the speed and cost optimized Qwen3.5 variant designed for high-throughput chat and… Multimodal · Open weights Open weights
Qwen 3.6 Max Preview Alibaba Qwen 3.6 Max Preview appears to be Alibaba’s newest preview flagship in the Qwen line, positioned a… Multimodal · Open weights Open weights
Qwen 3.6 Plus Alibaba Qwen3.6 Plus is Alibaba’s next-generation preview model in the Qwen Plus line, built with a hybrid… Multimodal · Open weights Open weights
Qwen 3.6 Plus Preview Alibaba Qwen3.6 Plus Preview is a preview large language model in the Qwen Plus line, built with a hybrid a… Multimodal · Open weights Open weights
Qwen 3.7 Max Alibaba Qwen3-Max is Alibaba Cloud’s closed-source trillion-parameter flagship LLM for coding, reasoning, e… Multimodal · Open weights Open weights
Qwen 3.8 Max Alibaba Qwen3.8 Max is a 2.4 trillion parameter Mixture of Experts flagship model with native vision langua… Multimodal · Open weights Open weights
Qwen Audio 3.0 ASR Flash Filetrans Alibaba Qwen Audio 3.0 ASR Flash Filetrans is a non real time speech recognition model that transcribes upl… Audio · Open weights Open weights
Qwen Audio 3.0 ASR Flash Streaming Alibaba Qwen Audio 3.0 ASR Flash Streaming is a real time speech recognition model that transcribes live au… Audio · Open weights Open weights
Qwen Audio 3.0 Realtime Flash Alibaba Qwen Audio 3.0 Realtime Flash is Alibaba's speed optimized real time duplex voice dialogue model. I… Audio · Open weights Open weights
Qwen Audio 3.0 Realtime Plus Alibaba Qwen-Audio-3.0-Realtime-Plus is a real-time duplex speech interaction model from Alibaba's Qwen fam… Audio · Open weights Open weights
Qwen Audio 3.0 TTS Alibaba Qwen Audio 3.0 TTS is a production oriented text to speech model built on a 12.5 Hz speech tokenize… Audio · Open weights Open weights
Qwen Code Qoder Alibaba Qwen-Coder-Qoder is a reinforced code model based on Qwen-Coder, custom trained for the Qoder agent… Coding · Open weights Open weights