NVIDIA GPT-OSS-120B Eagle3 is an optimized version based on the OpenAI gpt-oss-120b model. It adopts the Mixture of Experts (MoE) architecture, with a total of 120 billion parameters and 5 billion active parameters. This model supports both commercial and non-commercial use and is suitable for text generation tasks, especially for the development of AI Agent systems, chatbots, and other applications.

Natural Language ProcessingSafetensors

GLM-4.5-Air is a foundation model for agents launched by Zhipu AI. It adopts a compact design, unifying reasoning, coding, and agent capabilities to meet the complex requirements of agent applications. The model has a moderate number of parameters and superior efficiency. Multiple versions have been open-sourced and can be used for commercial purposes and secondary development.

Natural Language ProcessingTransformersMultiple Languages

NVIDIA-Nemotron-Nano-9B-v2 is a large language model trained from scratch by NVIDIA, designed for both inference and non-inference tasks. It adopts the Mamba2 - Transformer hybrid architecture, supports multilingual processing, has controllable inference capabilities, allows users to specify the thinking budget, and performs excellently in commercial applications and AI agent systems.

Natural Language ProcessingTransformersMultiple Languages

Llama 4 Maverick is a 17-billion-parameter multimodal Mixture of Experts (MoE) model from Meta, supporting 12 languages and image understanding, suitable for commercial and research applications.

MultimodalTransformersMultiple Languages

INT8 quantized version of Qwen2.5-7B-Instruct, suitable for multilingual scenarios in both commercial and research applications, optimized for memory requirements and computational throughput.

Natural Language ProcessingSafetensorsEnglish

A 3-billion parameter instruction-tuned language model developed by IBM, based on Granite-3.0 architecture, supporting multilingual tasks and commercial applications

Natural Language ProcessingTransformers

Phi-3-Small-8K-Instruct is a 7B-parameter lightweight open-source model focused on high-quality reasoning capabilities, supporting 8K context length, suitable for commercial and research applications in English environments.

Natural Language ProcessingTransformersOther