ZygAI is a fast local large language model designed specifically for Lithuanian and English tasks and is in the testing phase. As a lightweight bilingual assistant, it can run in real-time on local hardware, providing users with efficient and accurate bilingual services.

Natural Language ProcessingGgufMultiple Languages

Cyber Intelligence Brain is a large language model specifically fine-tuned for Capture the Flag (CTF) challenges and network security tasks. It is based on the Llama-3.1-8B-Instruct architecture and can assist in solving CTF problems, analyzing security vulnerabilities, conducting reverse engineering and cryptography challenges, and providing vulnerability exploitation reasoning while adhering to ethical guidelines.

Natural Language ProcessingSafetensorsMultiple Languages

Omni L1B3RT4S GENIE is an AI assistant fine-tuned based on the Qwen2.5-3B Instruct architecture. It is trained with customized examples of 1,103 elf characters, and has unique voice and loyalty modes, capable of providing users with a unique dialogue experience.

Natural Language ProcessingGgufEnglish

This is the latest cutting-edge model in the field of accuracy, dedicated to achieving artificial grain intelligence, and has made significant progress with the assistance of the world's top grain planting teams. This model is based on the Qwen3-0.6B architecture and is fully fine-tuned locally using an RX 9070 XT graphics card and the unsloth tool.

Natural Language ProcessingSafetensorsEnglish

KaniTTS is a high-speed, high-fidelity Arabic text-to-speech model optimized for real-time conversational artificial intelligence applications. It adopts a two-stage pipeline architecture, combining a large language model with an efficient audio codec to achieve excellent speed and audio quality, and can meet the speech synthesis needs of multiple fields such as conversational AI, accessibility assistance, and research.

Audio ProcessingTransformersArabic

Granite-4.0-Micro is a long-context instruction model developed by IBM with 3 billion parameters, fine-tuned from Granite-4.0-Micro-Base. This model uses an open-source instruction dataset and an internal synthetic dataset, and has enhanced instruction-following and tool invocation capabilities. It supports multilingual tasks and can serve as a base model for AI assistants in various fields.

Natural Language ProcessingTransformers

zen-agent-4b is an intelligent agent for tool invocation with 4 billion parameters, supporting the Model Context Protocol (MCP), which provides strong assistance for text generation tasks. This model is developed by Zen Research DAO, affiliated with the non - profit organization Zoo Labs Inc.

Natural Language ProcessingTransformersEnglish

This is the GGUF quantized version of the Qwen/Qwen3-Coder-30B-A3B-Instruct language model, optimized for local inference and supporting frameworks such as llama.cpp, LM Studio, OpenWebUI, and GPT4All. This model is a code generation and programming assistant model with a parameter scale of 30B.

Natural Language ProcessingGgufMultiple Languages

Granite-4.0-H-Small is a long-context instruction model with 32 billion parameters developed by IBM, specifically designed for enterprise-level AI assistants and supporting multiple languages and professional application scenarios.

Natural Language ProcessingTransformers

Granite-4.0-Micro is a 3-billion-parameter long-context instruction model developed by IBM. It has excellent instruction-following and tool invocation capabilities, supports multiple languages, and is suitable for business applications and AI assistant scenarios.

Natural Language ProcessingTransformers

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.

Hermes 4 14B is a cutting-edge hybrid mode reasoning model developed by Nous Research based on Qwen 3 14B. It has significant improvements in mathematics, code, STEM, logical reasoning, creativity, and format-fidelity output, while maintaining the quality of a general assistant and broad neutral alignment.

Natural Language ProcessingTransformersEnglish

This is a conversational AI assistant focused on Finnish dental medicine. It is a large language model fine-tuned with LoRA and can generate structured clinical responses for dental consultation questions, divided into three parts: background, assessment, and suggestions.

Natural Language ProcessingTransformersOther

cudaLLM-8B is a professional language model developed by ByteDance Seed, specifically designed to generate high-performance and syntactically correct CUDA kernel code. Built on the Qwen3-8B base model, it is trained through two stages of supervised fine-tuning and reinforcement learning, enabling it to assist developers in writing efficient GPU parallel programming code.

Natural Language ProcessingTransformersEnglish

Qwen3-Coder-30B-A3B-Instruct is an efficient text generation model optimized specifically for coding tasks. It has excellent long context processing capabilities and tool call support, providing powerful coding assistance for developers.

Natural Language ProcessingSafetensors

This is a code generation model in MLX format converted from Qwen/Qwen3-Coder-30B-A3B-Instruct, specifically optimized for Apple Silicon, supporting 8-bit weight quantization, and suitable for code generation and programming assistance tasks.

Natural Language ProcessingMlx

This is a French medical assistant model based on the MedGemma architecture, specifically optimized for the French medical field. The model provides the GGUF quantization format, supports multiple quantization levels, and is suitable for French medical text generation tasks such as medical consultation, symptom analysis, and prevention advice.

Natural Language ProcessingGgufFrench

The A3ON-1B Quantized Model is a multi-quantized version based on the kaiiddo/A3ON-1B base model, specifically optimized for text generation and code assistance scenarios. It offers different quantization options from extremely low bitrates to high quality, suitable for resource-constrained environments and high-precision requirement scenarios.

Natural Language ProcessingTransformersEnglish

A statically quantized version of the A3ON-1B model, suitable for tasks such as text generation and code assistance. This model is based on the kaiiddo/A3ON-1B base model and offers multiple quantization versions to meet different performance requirements.

Natural Language ProcessingTransformersEnglish

Medical Gemma-3N is a version fine-tuned specifically for emergency medical assistance and offline medical applications based on Google's Gemma-3N-4B model. This model was trained on 86,667 medical Q&A pairs, focusing on providing accurate first aid guidance and medical consultations, especially suitable for emergency situations with limited network connectivity.

Natural Language ProcessingSafetensorsEnglish