Z-Image-Re-Turbo is a text-to-image generation model that has been optimized for de-reduction and re-acceleration based on the Z-Image-De-Turbo model. This model aims to balance the convenience during training and the speed during inference. It restores the fast generation ability close to the original Turbo model while maintaining the same training-friendly features as Z-Image-De-Turbo, enabling it to be perfectly compatible with a large number of trained LoRA models in the Z-Image ecosystem.

MultimodalDiffusers

This project provides a text generation model fine-tuned based on the Microsoft Phi-3.5-mini-instruct model, which has been converted to the GGUF format and is suitable for the llama.cpp inference framework. The model was fine-tuned on the philschmid/guanaco-sharegpt-style dataset, optimizing its instruction-following and dialogue capabilities, and is suitable for efficient text generation tasks in resource-constrained environments.

Natural Language ProcessingGguf

FLUX.2-dev is an image generation and editing model developed by black-forest-labs. It has been converted to the GGUF format, optimized specifically for image generation tasks, and adopts a diffusion model architecture. It supports use in the ComfyUI framework.

MultimodalGguf

This is a video understanding model based on the VideoMAE architecture. It has been fine-tuned on the basis of pre-training on the Kinetics dataset and is specifically designed for sign language recognition tasks. The model's performance on the evaluation set needs improvement, with an accuracy of 0.0010.

Computer VisionTransformers

This is a video understanding model based on the VideoMAE-base architecture, which has been fine-tuned for 20 epochs on an unknown dataset. The model's performance on the evaluation set is limited, with an accuracy of 0.0041 and a loss value of 7.7839.

Computer VisionTransformers

Gemma 3 is a lightweight open-source multimodal model launched by Google. This version is an instruction-tuned quantization-aware training model with 12B parameters, which has been converted to the MXFP4 format of the MLX framework. It supports text and image input and generates text output, with a 128K context window and support for over 140 languages.

MultimodalMlx

This is a bidirectional autoregressive Transformer model based on the 🤗 Transformers library and has been uploaded to the model hub. The model card is automatically generated by the system, and specific technical details and application information need to be further supplemented.

Natural Language ProcessingTransformers

Qwen-SEA-LION-v4-4B-VL is a vision-language model with 4 billion parameters built on the Qwen3-VL-4B-Instruct architecture. It has been specifically instruction fine-tuned for the Southeast Asian region, possessing multilingual and multicultural capabilities, supporting English and seven Southeast Asian languages, and retaining strong vision-language understanding capabilities.

MultimodalTransformersMultiple Languages

This is a large language model with 172B parameters obtained by uniformly pruning 25% of the experts in MiniMax-M2 using the REAP method. It has been optimized and quantized specifically for llama.cpp, supporting multiple quantization levels and can run in LM Studio or projects based on llama.cpp.

Natural Language ProcessingGgufEnglish

This project provides a quantized version of the cerebras/MiniMax-M2-REAP-172B-A10B model, aiming to make knowledge accessible to the public. This is a large language model with 172 billion parameters, which has been optimized and quantized to reduce deployment costs and improve inference efficiency.

Natural Language ProcessingGguf

Wan2.2-TI2V-5B-Turbo-GGUF is an image-to-video model converted from the quanhaol/Wan2.2-TI2V-5B-Turbo base model. It has been optimized to run on a 4GB GPU and has excellent versatility and efficient inference capabilities.

MultimodalGguf

This is an experimental quantized version of the dense model based on Qwen3-4B-Thinking-2507. It adopts the innovative MXFP4 mixed quantization technology, aiming to explore the combination of weights with different precisions (such as MXFP4, Q8_0, Q6_K, etc.) to significantly reduce the model file size, improve the inference speed (TPS), and at the same time, maintain the precision as close as possible to the original F16 model. This project demonstrates the potential of the mixed quantization method, but it has been replaced by the author's updated version.

Natural Language ProcessingSafetensorsOther

Stable Diffusion v2-1-base is a diffusion model for text-to-image generation, which has been fine-tuned with an additional 220k steps based on v2-base. This model can generate and modify images according to text prompts, support multiple resolution outputs, and is suitable for various fields such as artistic creation and educational research.

Computer VisionDiffusers

Uni-MoE 2.0-Image is a visual generation model derived from Uni-MoE 2.0-Omni. It has been specifically fine-tuned on visual generation data and has powerful image generation and editing capabilities.

MultimodalDiffusersMultiple Languages

This is the MXFP4_MOE quantized version of the MiniMax-M2-THRIFT model. It has been compressed based on the original model, including 25% expert pruning (from 256 to 192) and setting top_k=8. Meanwhile, it retains the characteristics of the encoding model and can be used for text generation tasks.

Natural Language ProcessingGguf

NV-Reason-CXR-3B GGUF is a quantized version of the NVIDIA NV-Reason-CXR-3B vision-language model, optimized for edge device deployment. This is a model with 3 billion parameters, focusing on chest X-ray analysis. It has been converted to the GGUF format and quantized for efficient operation on mobile devices, desktops, and embedded systems.

MultimodalGgufEnglish

Qwen3-VL is a new-generation vision-language model launched by Alibaba, which has been comprehensively upgraded in text understanding, visual perception, spatial understanding, long context processing, and agent interaction, and supports flexible deployment from edge devices to the cloud.

MultimodalTransformers

Qwen3-VL is the most powerful vision-language model in the Tongyi series. It adopts a Mixture of Experts (MoE) architecture and provides weights in the GGUF format, supporting efficient inference on devices such as CPUs and GPUs. The model has been comprehensively upgraded in text understanding, visual perception, spatial understanding, video processing, etc.

MultimodalGguf

Qwen3-VL-8B-Thinking is the most powerful vision-language model in the Tongyi Qianwen series, with an 8B parameter version featuring enhanced reasoning capabilities. This model has been comprehensively upgraded in text understanding, visual perception, spatial understanding, long context processing, etc., and supports multimodal reasoning and agent interaction.

MultimodalGguf

Qwen3-VL-4B-Instruct is one of the most powerful vision-language models in the Tongyi series. It has been comprehensively upgraded in text understanding, visual perception, spatial understanding, video processing, etc. It supports running on a variety of hardware devices and has excellent multimodal reasoning capabilities.

MultimodalTransformers