# Chinese Support

This model is an MLX format version converted from deepseek-ai/deepseek-r1-0528-Qwen3-8B, suitable for local inference on Apple devices.

Qwen3-30B-A3B-8bit is an MLX format conversion version of the Qwen/Qwen3-30B-A3B model, supporting efficient operation on Apple chips.

This model is a 4-bit quantized version of Qwen3-32B in MLX format, optimized for efficient operation on Apple Silicon devices.

Light-R1-14B-DS is a 14B-parameter quantized large language model supporting text generation tasks, designed for efficient inference in resource-constrained environments.

Tencent Hunyuan3D 2mini is a lightweight and efficient image-to-3D model with 600 million parameters, supporting both Chinese and English inputs.

Qwen2-VL-2B is a vision-language model that provides a quantized version in GGUF format, suitable for various scenarios.

Hunyuan Video is a text-to-video generation model developed by Tencent.

FLUX.1-dev is a text-to-image diffusion model quantized to INT8 format using Optimum Quanto, suitable for non-commercial use.

Lawyer LLaMA is a large language model based on the LLaMA architecture, specializing in Chinese legal tasks.

A classification model based on the DistilBERT architecture, fine-tuned using the TextAttack framework, achieving 90.04% accuracy on the evaluation set.

SigLIP is a vision-language pre-trained model suitable for zero-shot image classification tasks.

Storytime 13B is a large language model based on the LLaMA architecture, specializing in Chinese text generation tasks, particularly excelling in story creation.

This is an image captioning model based on the BLIP architecture, capable of generating concise textual descriptions for input images.

This is a binary classification model trained using AutoTrain, specifically designed to distinguish between spam and non-spam emails.

This is a plain old model with unspecified specific functions and purposes.

A model for classifying emoji description texts, suitable for social media and instant messaging applications.

A Q&A model fine-tuned on the SQuAD v2.0 dataset based on Electra-small-discriminator, suitable for distinguishing answerable from unanswerable questions