MiniMax-M2-4bit is a 4-bit quantized version converted from MiniMaxAI/MiniMax-M2 using the mlx-lm tool. It is specifically optimized for Apple Silicon chips and provides efficient text generation capabilities.

Natural Language ProcessingMlx

Qwen3-Next-80B-A3B-Thinking is a quantized version based on the Qwen3-Next-80B-A3B-Thinking model, specifically optimized for text generation tasks. This model needs to be used in conjunction with version PR 16095 of llama.cpp and offers multiple quantization levels to adapt to different hardware configurations.

Natural Language ProcessingGguf

DeepSeek-OCR-8bit is an MLX format version converted from the DeepSeek-OCR model. It is a visual language model specifically optimized for Apple chips, supporting multilingual OCR recognition and image text understanding tasks.

MultimodalMlxOther

This model is a vision-language model in MLX format converted from DeepSeek-OCR, specifically designed for optical character recognition (OCR) tasks. It supports multilingual text recognition and image understanding.

MultimodalMlxOther

This is a text generation model that is specifically fine-tuned based on the Google Gemma-3 model. After training, it can use external tools to generate step-by-step plans. This model is trained on the rewoo/planner_instruction_tuning_2k dataset and uses LoRA technology for efficient fine-tuning.

Natural Language ProcessingTransformers

Svara-TTS is an open-source multilingual text-to-speech model for Indian languages, supporting 19 languages (18 Indian languages + Indian English). This model is built based on the Orpheus-style discrete audio token method, aiming to achieve clear, expressive, and low-latency speech synthesis on ordinary GPUs/CPUs.

Audio ProcessingTransformersMultiple Languages

This is an MLX format model converted from the DeepSeek-OCR model, supporting multilingual image text recognition and text generation functions, specifically optimized for OCR tasks.

MultimodalMlxOther

A dedicated novel writing model fine-tuned based on the command-a-03-2025-uncut model, trained with a high-quality novel paragraph dataset, supporting multilingual novel writing tasks

Natural Language ProcessingTransformersMultiple Languages

P1 - 30B - A3B is a large language model with 30 billion parameters. It has been processed by MXFP4_MOE quantization, which optimizes the inference efficiency while maintaining the model performance and is suitable for text generation tasks.

Natural Language ProcessingGguf

This is a Lora image fusion tool based on the Qwen-Edit model, specifically designed for image-to-image conversion tasks. It can achieve excellent image fusion effects and is particularly good at image editing functions such as white model to material conversion.

Computer VisionDiffusers

This is the MXFP4_MOE quantized version of the PromptCoT-2.0-SelfPlay-30B-A3B model, specifically designed for text generation tasks. The model adopts chain of thought prompting and self-play training techniques, and achieves more efficient inference performance through quantization optimization.

Natural Language ProcessingGguf

DeepSeek-OCR-bnb-4bit-NF4 is a 4-bit NF4 quantized version of deepseek-ai/DeepSeek-OCR, created using bitsandbytes. While maintaining high accuracy, it significantly reduces video memory usage (up to 8GB), making it very suitable for consumer-grade GPUs.

MultimodalSafetensorsOther

This is the MXFP4 quantized version of Qwen3-Next-80B-A3B-Thinking, which uses advanced quantization technology to significantly reduce storage and computational requirements while maintaining model performance. As an experimental version, it demonstrates the latest achievements in quantization technology.

Natural Language ProcessingGguf

This is the MXFP4_MOE quantized version of the Huihui-gpt-oss-20b-BF16-abliterated-v2 model, specifically optimized for text generation tasks. The model reduces the model size through quantization technology while maintaining good generation performance.

Natural Language ProcessingGguf

This is an MXFP4 quantized experimental version of Qwen3-Next-80B-A3B-Instruct, developed based on cutting-edge quantization technology, providing efficient text generation capabilities. This version is experimental and requires a special version of llama.cpp support.

Natural Language ProcessingGguf

This is an MXFP4 Mixture-of-Experts quantized version based on the Intern-S1 model, specifically optimized for image-text-to-text tasks. It improves inference efficiency through quantization technology.

MultimodalGguf

This is the latest cutting-edge model in the field of accuracy, dedicated to achieving artificial grain intelligence, and has made significant progress with the assistance of the world's top grain planting teams. This model is based on the Qwen3-0.6B architecture and is fully fine-tuned locally using an RX 9070 XT graphics card and the unsloth tool.

Natural Language ProcessingSafetensorsEnglish

LongCat-Video is a basic video generation model with 13.6 billion parameters, which performs excellently in generation tasks such as text-to-video, image-to-video, and video frame continuation. It is particularly good at efficient and high-quality long video generation.

MultimodalDiffusersMultiple Languages

This is a semantic similarity calculation model based on the Cross Encoder architecture. It fine-tunes the Reason-ModernColBERT base model on the LangCache sentence pair dataset. This model is specifically designed to calculate the similarity scores between text pairs and is suitable for tasks such as sentence pair classification and semantic caching.

Natural Language ProcessingSentence-transformersEnglish

This is a LoRA fine-tuned model based on Qwen-Image-Edit-2509, specifically designed for the image fusion task of converting white background images to specific scenes, and performs extremely well.

Computer VisionDiffusers