# Multilingual support

Gemma 3n-E2B-it is a lightweight open-source multimodal model launched by Google, built on the same technology as Gemini and optimized for low-resource devices.

Mistral-Small-3.2-24B-Instruct-2506 is an image-text-to-text model that performs excellently in model quantization and shows significant improvements in instruction following, reducing repetition errors, and function calls.

Mistral-Small-3.2-24B-Instruct-2506 is an image-text-to-text model and an updated version of Mistral-Small-3.1-24B-Instruct-2503, with improvements in instruction following, reducing repetition errors, and function calls.

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google, built on the same research and technology as the Gemini model. It supports text, audio, and visual inputs and is suitable for various tasks.

A Korean sentence transformer fine-tuned based on intfloat/multilingual-e5-small for Korean retrieval tasks

This is a 4-bit DWQ quantized version converted from Qwen/Qwen3-Embedding-8B, suitable for the embedding model of the MLX framework.

This is a transformers model for zero-shot classification tasks, which can classify text without a large amount of labeled data.

PP-OCRv4_server_det is a text detection model developed by the PaddleOCR team, suitable for high-performance server deployment with high accuracy.

The quantized version of Qwen3-Reranker-0.6B, dedicated to making knowledge accessible to everyone.

This is an automatically generated transformers model card, and specific information is to be supplemented.

A large language model developed by DeepSeek AI, optimized with 4-bit quantization, suitable for Apple chip devices.

NuExtract 2.0 is a series of multimodal and multilingual models trained specifically for structured information extraction tasks, developed based on the QwenVL series of pre - trained models.

LLM-jp-3.1-1.8b is a large language model developed by the National Institute of Informatics in Japan. Based on the LLM-jp-3 series, it incorporates instruction pre-training to enhance the instruction-following ability.

NuExtract 2.0 is a series of multimodal models specifically trained for structured information extraction tasks. It supports text and image inputs and has multilingual processing capabilities.

This is a transformers model that has been pushed to the Hub. The specific functions and uses are to be supplemented.

This is a transformers model that has been uploaded to the Hugging Face Hub. Specific information is to be supplemented.

This is an automatically generated transformers model card, lacking specific model information.

LLM-jp-3.1-13b-instruct4 is a large language model developed by the National Institute of Informatics in Japan. It significantly improves the instruction-following ability through instruction pre-training and supports multiple languages such as Japanese and English.

This model is a GGUF format conversion based on PocketDoc/Dans-PersonalityEngine-V1.3.0-12b, supporting multiple languages and tasks, suitable for general purposes, role-playing, story creation, and other scenarios.

A large language model based on the Gemma architecture, specialized in Turkish text generation tasks.

A multilingual, multi-purpose large language model supporting various professional domains and general tasks, suitable for role-playing, story creation, programming, and other scenarios.

This is a sentence-transformers model fine-tuned from intfloat/multilingual-e5-small, specifically optimized for Korean retrieval tasks, mapping text to a 384-dimensional vector space.

This is a transformers model published on the Hugging Face Hub, and specific information is to be supplemented.

Xiaolong-Qwen3-14B is a large language model based on the Qwen3 architecture, with a parameter scale of 14 billion, focusing on text generation tasks.

The quantized model of Qwen2.5 VL 7B Instruct is a powerful multimodal model that supports image and text input and generates text output, with wide application value in multiple fields.

trurl-2-13b is a large language model with a parameter scale of 13B, providing a quantized version in GGUF format, suitable for various natural language processing tasks.

An open-source code reasoning large language model developed by NVIDIA, with a parameter scale of 14 billion, focused on code generation and reasoning tasks.

NuExtract 2.0 is a series of multimodal models specifically trained for structured information extraction tasks. It supports text and image inputs and has the ability to process multiple languages.

Qwen3-8B-AWQ is the latest generation of large language model with 8.2B parameters in the Tongyi Qianwen series, which uses AWQ 4-bit quantization technology to optimize inference efficiency. It supports the switching between thinking and non-thinking modes and has excellent reasoning, instruction-following, and intelligent agent capabilities.

Qwen3-30B-A3B-AWQ is an AWQ quantized version based on the Qwen3-30B-A3B model, suitable for text generation tasks and supporting the switching between thinking mode and non-thinking mode.

Qwen2.5-Omni is an end-to-end multimodal model capable of perceiving various modalities including text, images, audio, and video, while synchronously generating text and natural speech responses in a streaming manner.

A quantized text generation model with output and embedding tensors in f16 format, while other tensors use q5_k or q6_k quantization, resulting in a smaller size with performance comparable to the pure f16 version.

This repository contains GGUF format model files for Qwen/Qwen3-0.6B, quantized by TensorBlock's machines and compatible with llama.cpp.

The TEN Turn Detection System is an intelligent turn detection model specifically designed for natural dynamic human-machine interaction, accurately identifying natural turn-taking signals to achieve context-aware reasonable interruptions.

Qwen3-8B-Base is the latest generation of Tongyi's large model series, with 8.2 billion parameters and support for 119 languages. It is suitable for a variety of natural language processing tasks.

Qwen3-1.7B is the latest 1.7 billion parameter base language model in the Qwen series, featuring a three-stage pre-training system and supporting 32k context length.

Qwen3-4B-Base is the latest generation of the Qwen series' 4-billion-parameter large language model, pre-trained on 36 trillion tokens of multilingual data, supporting a 32k context length.

This model is based on the transformers library, and its specific functions and uses require further information to be supplemented.

English-Spanish translation model fine-tuned on the opus100 dataset based on t5-small

This is a speech recognition model fine-tuned on the Common Voice dataset based on facebook/wav2vec2-xls-r-300m, supporting Irish language.