This NVIDIA-hosted quantized version of the Qwen 3.5 397B (with 17B active parameters) model supports vision and video inputs in addition to text. It includes advanced prompting templates for tool use and multimodal content. The model is designed for high-performance inference using NVIDIA-optimized stacks.
Qwen3.5 397B A17B is a Foundation models & chat product. It focuses on enabling efficient local inference of very large multimodal models through quantization and MoE architecture. Qwen3.5 397B A17B is an open-source project aimed at developers building multimodal applications. The project is open source (Apache-2.0). It runs on the web and API.
Behind Qwen3.5 397B A17B is NVIDIA, based in the United States, and the product first shipped in 2024. The project is developed in the open on GitHub with 3.3k stars and 356 commits in the last 90 days. PulseGate's similarity index places it among 9 comparable tools. Among its 4 catalogued features are Vision Understanding, Video Processing, and Tool Integration.
Latest indexed changes and source events
nvidia/Qwen3.5-397B-A17B-NVFP4 verified by the PulseGate indexer
Other apps tracked under the same category.
