VieNeu-TTS-1000h is an advanced Vietnamese edge-side text-to-speech model. It is trained on approximately 1000 hours of high-quality Vietnamese speech data, has an instant voice cloning function, supports seamless switching between Vietnamese and English, and can synthesize 24kHz waveforms in real-time on CPU or GPU.

Audio ProcessingTensorboardOther

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 the most powerful vision - language model in the Tongyi series, with comprehensive upgrades in text understanding and generation, visual perception and reasoning, context length, spatial and video dynamic understanding, and agent interaction capabilities. This model offers both dense architecture and mixture - of - experts architecture, supporting flexible deployment from edge devices to the cloud.

MultimodalTransformers

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 has been comprehensively upgraded in aspects such as text understanding and generation, visual perception and reasoning, context length, spatial and video dynamic understanding, and agent interaction capabilities. This model offers both dense architecture and mixture - of - experts architecture, supporting flexible deployment from edge devices to the cloud.

MultimodalGguf

Qwen3-VL-32B-Thinking is the most powerful vision-language model in the Qwen series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, strong spatial and video dynamic understanding abilities, and outstanding agent interaction capabilities. This version adopts a thinking architecture for enhanced reasoning, supporting dense architectures from edge to cloud and mixture-of-experts model architectures.

MultimodalTransformers

This project performs llama.cpp mixed-precision quantization on DeepSeek-V3-0324, solving the problem of model deployment on edge devices and improving the model's operation efficiency and resource utilization.

Natural Language ProcessingTransformers

KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. It adopts a two-stage pipeline architecture, combining a large language model and an efficient audio codec, achieving excellent speed and audio quality. It supports multiple languages and is suitable for edge/server deployment.

Audio ProcessingTransformersMultiple Languages

Zen Nano 0.6B is the smallest model in the Zen model family, optimized for edge deployment and capable of running efficiently on edge devices, providing strong support for related applications.

Natural Language ProcessingSafetensorsEnglish

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment. It sets a new standard in terms of quality, speed, and memory efficiency. This model adopts an innovative hybrid Liquid architecture with multiplicative gates and short convolutions, supporting multilingual processing.

Natural Language ProcessingTransformersMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment. This model sets a new standard in terms of quality, speed, and memory efficiency, and is particularly suitable for running in resource-constrained environments.

Natural Language ProcessingGgufMultiple Languages

NeuTTS Air is the world's first ultra-realistic, edge-side text-to-speech (TTS) language model with instant voice cloning capabilities. Built on a large language model backbone with 0.5B parameters, it brings natural voice, real-time performance, built-in security, and speaker cloning capabilities to local devices.

Audio ProcessingGguf

Qwen3-VL is the most powerful vision-language model in the Tongyi large model series, with significant improvements in text understanding and generation, visual perception and reasoning, context length, spatial and video dynamic understanding, and agent interaction capabilities. This model offers both dense architecture and mixture-of-experts model architecture, supporting deployments of different scales from the edge to the cloud.

MultimodalTransformers

MiniCPM4.1-8B GGUF is an efficient large language model designed specifically for edge devices. It has carried out systematic innovations in four key dimensions: model architecture, training data, training algorithm, and inference system, achieving extreme efficiency improvement. It supports a context length of 65,536 tokens and a hybrid inference mode.

Natural Language ProcessingTransformersMultiple Languages

This is a statically quantized version of the LiquidAI/LFM2-350M-ENJP-MT model, supporting bidirectional translation tasks between English and Japanese. It is optimized for edge computing scenarios and offers various quantization options to meet different hardware requirements.

Natural Language ProcessingTransformersMultiple Languages

This is a code generation model optimized for the Rockchip RK3588 development board, converted from Qwen2.5-Coder-3B-Instruct, and supports localized code assistance and generation tasks on edge devices.

MiniCPM4.1-8B-GGUF is a GGUF quantized format version of the MiniCPM4.1-8B model. It is an efficient large language model designed for edge devices, with 8 billion parameters, supporting integrated thinking, and can achieve more than 5 times the generation acceleration on typical edge chips.

Natural Language ProcessingTransformersMultiple Languages

Kuaishou Keye-VL is a cutting - edge multimodal large language model developed by the Kuaishou Keye team, which performs excellently in video understanding, visual perception, and reasoning tasks. The 1.5 version reaches a new height in video understanding, image perception, and reasoning ability through innovative fast - slow video encoding strategies, LongCoT cold - start data pipelines, and reinforcement learning training strategies, and supports an extended context length of up to 128k tokens.

MultimodalSafetensorsMultiple Languages

This is a statically quantized version based on the kshitijthakkar/loggenix-moe-0.3B-A0.1B model, specifically optimized for low-resource environments and edge AI applications, offering multiple quantization levels.

Natural Language ProcessingTransformersEnglish

This is the TensorFlow Lite converted version of the sentence-transformers/all-MiniLM-L6-v2 model, specifically optimized for edge devices. This model can map text to a 384-dimensional vector space and supports tasks such as semantic search and text similarity calculation. It provides two versions: Float32 and INT8 quantization. The quantized version reduces the model size by approximately 4 times and significantly improves the running speed on the CPU.

Natural Language ProcessingLitertEnglish