Trending Open LLM models

Advanced version of the DeepSeek model designed for complex tasks.

Base version of the DeepSeek model with improved capabilities.

Preview of a smaller-scale thinking model with 3 billion parameters.

Development version of the FLUX model for versatile applications.

Kokoro model with 82 million parameters focused on empathy in responses.

Instruction-tuned version of the Llama model with 70 billion parameters.

Embedding-focused model based on ModernBERT architecture.

Base version of a modern BERT model optimized for various NLP tasks.

Preview of the QVQ model featuring 72 billion parameters for enhanced performance.

Large version of the Stable Diffusion model for generating high-quality images.

Video processing AI model developed by Tencent.

Mixed model focused on generating seamless journeys in artwork.

Specialized model from Datou aimed at creative tasks.

Fast version of the FLUX model aimed at real-time applications.

32 billion parameter preview model from Qwen for performance demonstration.

Instruction-based version of Llama featuring 8 billion parameters.

Lightweight sentence transformer optimized for similarity and search tasks.

Large-scale version of ModernBERT for handling extensive datasets.

Dynamic model designed for tango-like interactions.

1 billion parameter version of the Llama model, optimized for efficiency.

Baseline model of Stable Diffusion with Extended capabilities.

Text-to-speech model focusing on realistic vocal output.

Turbo-optimized version of Whisper for fast speech-to-text conversions.

Video generation model from Lightricks optimized for various video tasks.

Compact model designed for effective language understanding.

Instruction-based variation of the Qwen2 model for visionary tasks.

NSFW content detection model designed for studio applications.

Vision-instruct version of Llama with 11 billion parameters.

Version of FLUX specialized for logo design tasks.

A coding-focused version of the Qwen2.5 model with instruction capabilities.

A mini version of Ruyi model optimized for resource efficiency.

Developmental filling model for art and creative expressions.

Speech recognition model tailored for aquatic environment analysis.

Large image analysis model by JeffreyXiang.

8B parameter GPT model tailored for versatile AI tasks.

Large-scale speech recognition model geared for diverse applications.

Realism-focused visual model designed for creative outputs.

GGUF version of the development model for FLUX.

Embeddings optimized for semantic search and language understanding.

Instruction-tuned 8B model for a variety of tasks.

Focuses on enhancing emoji generation and contextual interactions.

Gemma model, designed for various interactive tasks.

Fifth version of the Stable Diffusion model for generating images.

Essential BERT model designed for general NLP tasks.

Instruction model variant with a focus on natural language processing.

Small-scale thinking model preview for AI applications.

Text encoding model tailored to support various textual tasks.

Comfortable interaction model for video processing.

Heavyweight instruction model in multiple expert modes.

Instruction-based version of Meta Llama with 8 billion parameters.

7B instruction-focused model tailored for diverse AI tasks.

Union model for controlling various types of tasks.

8 billion parameter version of the Llama model with advanced features.