Qwen3-30B-A3B-NVFP4 is an NVIDIA-optimized version of the Qwen3 model using NVFP4 quantization. It supports advanced tool calling and function calling through a detailed chat template. The model is designed for efficient inference on NVIDIA GPUs while preserving the capabilities of the original Qwen3 architecture.
In the Foundation models & chat space, Qwen3 30B A3B takes a focused approach. It focuses on running high-performance quantized versions of Qwen3 models on NVIDIA hardware. It is built as an open-source project for developers. The project is open source (Apache-2.0). It runs on the web and API.
NVIDIA builds and maintains Qwen3 30B A3B, and it first shipped in 2024. The project is developed in the open on GitHub with 3.3k stars and 354 commits in the last 90 days. The category is crowded — PulseGate's index counts 23 comparable projects. Key capabilities include Tool Calling, Function Calling, and NVFP4 Quantization.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do