Qwen3-32B is the latest generation of large language models in the Qwen series, with powerful reasoning, instruction-following, intelligent agent interaction, and multilingual processing capabilities. It supports over 100 languages and dialects and can seamlessly switch between thinking and non-thinking modes, providing users with a natural and smooth dialogue experience.

Natural Language ProcessingTransformers

This is an English-Spanish translation model fine-tuned on the Amazon dataset based on the Google mT5-small model, specifically designed for text abstract generation tasks. The model achieved scores of Rouge1: 16.44 and Rouge2: 8.04 on the evaluation set.

Natural Language ProcessingTransformers

Fyodor-StarCoder2-7B-MoE is an enhanced version based on StarCoder2-7B, adopting a Mixture of Experts architecture with 3 MoE layers, 6 expert networks, and a top-2 routing mechanism. It performs excellently in code generation, function calls, and agent tasks.

Natural Language ProcessingTransformersOther

Trouper-12B GGUF is a text generation model developed by DarwinAnim8or based on the original model. It is specifically optimized for role-playing and creative writing scenarios. This model is fine-tuned from Mistral-Nemo-Base-12B and trained using a custom 'Actors' dataset. The generated text is more natural and avoids the common 'AI language' features.

Natural Language ProcessingGgufEnglish

This is an experimental mixed quantization model that uses the MXFP4_MOE mixed weight technology. While maintaining accuracy close to Q8, it achieves a smaller file size and higher inference speed. The model explores the combination of MXFP4 with high-precision embedding/output weights and achieves near-lossless optimization of accuracy on dense models.

Natural Language ProcessingGgufOther

Kimi - K2 - Thinking 3.825bit MLX is a quantized model for text generation. It achieves different perplexity performances in tests through different quantization methods. Among them, q3.825bit quantization can reach a perplexity of 1.256.

Natural Language ProcessingMlxEnglish

MiniMax-M2-REAP-162B-A10B is an efficiently compressed version of MiniMax-M2. It uses the REAP (Routing Weighted Expert Activation Pruning) method to reduce the model size by 30% while maintaining almost the same performance, compressing from 230B parameters to 162B parameters, significantly reducing the memory requirement.

Natural Language ProcessingTransformersEnglish

MiniMax-M2-REAP-172B-A10B is a memory-efficient compressed variant of MiniMax-M2. It uses the REAP expert pruning method, reducing the model size by 25% from 230B parameters to 172B parameters while maintaining almost the same performance.

Natural Language ProcessingTransformersEnglish

The BT4 model is the neural network model behind the LeelaChessZero engine, specifically designed for chess games. This model is based on the Transformer architecture and can predict the best next move based on historical moves, evaluate the game situation, and generate move probabilities.

Scientific ComputingTransformers

Prima-24B is a large language model with 24 billion parameters, which is quantized and optimized through the GGUF format and specifically optimized for role-playing and creative writing tasks. This model is converted from the original Prima-24B model, using the Q4_K_M quantization level, which significantly reduces the model size and memory requirements while maintaining good performance.

Natural Language ProcessingGgufEnglish

This is a sentence transformer model fine-tuned based on sentence-transformers/all-mpnet-base-v2, which can map text to a 768-dimensional dense vector space and support various natural language processing tasks such as semantic similarity calculation, semantic search, and text classification.

Natural Language ProcessingSentence-transformers

This is a statically quantized GGUF version of the Manoghn/voicecraft-mistral-7b model, based on the Mistral-7B architecture, specifically designed for content generation and text generation tasks. This version offers multiple quantization levels, ranging from 2.8GB to 14.6GB. Users can choose the appropriate version according to their hardware conditions and performance requirements.

Natural Language ProcessingTransformersEnglish

Jan-v2-VL is a vision-language model with 8 billion parameters, designed specifically for long-term, multi-step tasks in real software environments (such as browsers and desktop applications). It combines language reasoning with visual perception, can follow complex instructions, maintain intermediate states, and recover from minor execution errors.

MultimodalGguf

Jan-v2-VL is a vision-language model with 8 billion parameters, designed to execute long-term, multi-step tasks in real software environments such as browsers and desktop applications. It tightly integrates language reasoning with visual perception, can follow complex instructions, maintain intermediate states, and recover from minor execution errors to achieve stable and continuous task completion.

MultimodalTransformersEnglish

This is a video action recognition model fine-tuned on the WLASL dataset based on the VideoMAE-base architecture, specifically optimized for sign language recognition tasks, achieving an accuracy of 48.22% on the evaluation set.

Computer VisionTransformers

RealRobot_chatbot_llm is a professional product artificial intelligence model based on the Gemma3n architecture, specifically fine-tuned on the proprietary dataset of the RealRobot product catalog. This model can quickly create an accurate, cost-effective, and deployable professional language model based on the enterprise's own product data, providing highly specialized product Q&A services.

Natural Language ProcessingGgufMultiple Languages

Chonky is a multilingual paragraph segmentation model based on DistilBERT, fine-tuned on nearly 11 billion tokens from over 34 million Wikipedia articles. It can segment any natural language text into semantic chunks and supports 104 languages.

Natural Language ProcessingTransformersMultiple Languages

Chandra is a high-precision OCR model that can convert images and PDFs into structured outputs, such as Markdown, HTML, and JSON, while retaining detailed layout information. It supports more than 40 languages and is good at handling complex document elements.

MultimodalTransformersEnglish

This is the GGUF quantized version of the zerofata MS3.2-PaintedFantasy-v3-24B model, quantized using the llama.cpp tool, offering multiple quantization types to meet different hardware and performance requirements.

Natural Language ProcessingGguf

Moondream 3 Preview HF is a re-implementation of the Moondream 3 (Preview) model based on the HuggingFace Transformers architecture specification, making it fully compatible with the Hugging Face ecosystem. It is a multimodal vision-language model that uses a Mixture of Experts (MoE) text backbone, with approximately 9 billion parameters and 2 billion active parameters.

MultimodalTransformers