The NVIDIA Qwen3-30B-A3B-Thinking-2507 Eagle model is the Eagle head of the Alibaba’s Qwen3-30B-A3B-Thinking-2507 model, which is an auto-regressive language model that uses a mixture-of-experts (MoE) architecture with 32 billion activated parameters and 1 trillion total parameters. For more information, please check here. The NVIDIA Qwen3-30B-A3B-Thinking-2507 Eagle3 model incorporates Eagle speculative decoding with TensorRT Model Optimizer. Use of these model weights is governed by the nvidia-open-model-license. Additional Information: Apache License 2.0. Developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks. Hugging face 02/27/2026 via [https://huggingface.co/nvidia/Qwen3-30B-A3B-Thinking-2507-Eagle3] Architecture Type: Transformers Network Architecture: Llama3 Model Parameters: 120M Input Type(s): Text Input Format(s): String Input Parameters: One-Dimensional (1D): Sequences Other Properties Related to Input: Max Context Length: 262144 Output Type(s): Text Output Format: String Output Parameters: One-Dimensional (1D): Sequences Other Properties Related to Output: Max…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: nvidia
Теги: Model Optimizer, llama, nvidia, ModelOpt, Qwen3-30B-A3B-Thinking-2507, Eagle3
Лайков: 4 | Загрузок: 249
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
