GigaChat3-10B-A1.8B is an efficient dialogue model in the GigaChat series. Based on the Mixture-of-Experts (MoE) architecture, it has a total of 10 billion parameters and 1.8 billion active parameters. It adopts the innovative Multi-head Latent Attention (MLA) and Multi-token Prediction (MTP) technologies, aiming to optimize inference throughput and generation speed. The model is trained on 20T tokens of diverse data and supports 10 languages including Chinese, suitable for dialogue scenarios requiring quick responses.

Natural Language ProcessingGgufMultiple Languages

LongCat Image Editing is the image editing version of Longcat-Image. It is an open-source image editing model that supports both Chinese and English. It has reached the advanced level of open-source models in terms of instruction following, image quality, and visual consistency, and has excellent precise editing and consistency preservation capabilities.

MultimodalTransformersMultiple Languages

Qwen-Image is a text-to-image generation model developed based on the Qwen series. It supports both Chinese and English inputs and performs excellently on multiple evaluation metrics. It is particularly suitable for image generation scenarios that pursue realistic effects.

MultimodalDiffusersMultiple Languages

This is a static quantized version of the yanolja/YanoljaNEXT-Rosetta-27B-2511 model, providing weight files of various quantization types and supporting multilingual translation tasks. The model is specifically optimized for 32 languages, including major languages such as Chinese, English, Japanese, and Korean.

Natural Language ProcessingTransformersMultiple Languages

This project provides a GGUF quantized version of the `yanolja/YanoljaNEXT-Rosetta-4B-2511` model. This model is a large language model focused on multilingual translation tasks, supporting 33 languages including Chinese, English, Japanese, Korean, French, German, etc. The quantized version was created by mradermacher, offering a variety of quantization options with different precisions and file sizes, facilitating deployment and use in resource-constrained environments.

Natural Language ProcessingTransformersMultiple Languages

MOSS-TTSD is an open-source bilingual spoken dialogue synthesis model that supports Chinese and English. It can convert two-person dialogue scripts into natural and expressive dialogue voices. It supports voice cloning, and the maximum duration of single-round voice generation can reach 1700 seconds.

Audio ProcessingSafetensorsMultiple Languages

SoulX-Podcast-1.7B is a static quantized version based on Soul-AILab/SoulX-Podcast-1.7B, specifically designed for text-to-speech tasks. This model supports English and Chinese and offers multiple quantized versions to meet different hardware and performance requirements.

Natural Language ProcessingTransformersMultiple Languages

This is a quantized version of the afkfatih/LFM2-8B-A1B-TR model, offering various GGUF quantization formats. The model is a multilingual large language model with 8 billion parameters, specifically optimized for the Turkish language and supporting 9 languages including English, Chinese, and Arabic.

Natural Language ProcessingTransformersMultiple Languages

Tiny-Purr-350M is a conversational model fine-tuned based on LiquidAI/LFM2-350M. It is trained on the Tiny-Purr-2 dataset and has the ability to provide casual, friendly, and cat-themed conversational responses, supporting both Chinese and English.

Natural Language ProcessingPeftMultiple Languages

This is a lightweight version of the ByteDance Seed-OSS-36B-Instruct model quantized to 4 bits using DWQ. It is distilled from the BF16 teacher model using mlx-lm 0.27.1 and supports Chinese-English bilingual text generation tasks.

Natural Language ProcessingMlxMultiple Languages

GLM-4.6-4bit is a 4-bit quantized version converted from the zai-org/GLM-4.6 model using the mlx-lm tool. It is specifically optimized for Apple Silicon chips and supports Chinese and English text generation tasks.

Natural Language ProcessingMlxMultiple Languages

KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational artificial intelligence applications. The model uses a two-stage processing flow, combining a large language model and an efficient audio codec. On an Nvidia RTX 5080, the latency for generating 15 seconds of audio is only about 1 second, and the MOS naturalness score reaches 4.3/5. It supports multiple languages such as English, Chinese, and Japanese.

Audio ProcessingTransformersMultiple Languages

Hunyuan Image 2.1 is a text-to-image model based on the diffusers library. It can generate high-quality images according to text descriptions, supports both Chinese and English inputs, and provides users with a convenient image generation experience.

Computer VisionDiffusersMultiple Languages

This is the GGUF format quantized version of the moonshotai/Kimi-K2-Instruct-0905 model, using the ik_llama.cpp branch for optimal quantization. The model adopts a mixture of experts architecture, supports Chinese dialogue and text generation tasks, and has been optimized with various quantization schemes to significantly reduce memory usage while maintaining high quality.

Natural Language ProcessingGgufOther

The Hunyuan translation model is an advanced machine translation system developed by Tencent, including the translation model Hunyuan-MT-7B and the integrated model Hunyuan-MT-Chimera. This model supports mutual translation of 33 languages, including mainstream languages such as Chinese, English, and French, as well as five ethnic minority languages in China, and performed excellently in the WMT25 competition.

Natural Language ProcessingTransformers

YanoljaNEXT-Rosetta-20B is a multilingual translation model that supports mutual translation among 11 languages, including English, Chinese, Japanese, Korean, etc. This model has undergone static quantization processing and offers multiple quantization versions, significantly reducing the model size and computational resource requirements while maintaining translation quality.

Natural Language ProcessingTransformersMultiple Languages

Seed-OSS-36B-Instruct is a text generation model developed by ByteDance. It is based on a large language model architecture with a 36B parameter scale and is specifically optimized for instruction-following tasks. This model supports both English and Chinese and uses the Apache-2.0 open-source license. It can be efficiently deployed through the vllm and mlx inference frameworks.

Natural Language ProcessingMlxMultiple Languages

Seed-OSS-36B-Instruct is a large-scale language model developed by ByteDance, with 36 billion parameters, focusing on text generation tasks. This model is implemented based on the MLX framework, supports both English and Chinese, and has powerful instruction following and text generation capabilities.

Natural Language ProcessingMlxMultiple Languages

Seed-OSS-36B-Instruct is a large language model with 36 billion parameters developed by ByteDance. It is optimized based on the MLX framework and focuses on text generation tasks. This model supports both English and Chinese, and uses the Apache 2.0 open-source license. It has powerful instruction-following and content generation capabilities.

Natural Language ProcessingMlxMultiple Languages

This is the GGUF format version of the unsloth/Qwen3-30B-A3B-Instruct-2507 model, quantized by machines provided by TensorBlock. This model is a large language model with 30 billion parameters, specifically optimized for instruction following tasks and supporting multiple languages such as Chinese and English.

Natural Language ProcessingTransformers