Qwen3-Coder-Next-NVFP4 is a quantized version of the Qwen/Qwen3-Coder-Next model with weights and activations converted to FP4 data type. It enables efficient inference for coding and text generation tasks while significantly reducing memory requirements. The model is hosted on Hugging Face and supports standard Transformers usage with a provided chat template for conversational applications.
In the Coding AI & assistants space, Qwen3 Coder Next takes a focused approach. It focuses on running large coding language models efficiently on hardware with limited memory or specialized accelerators. 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.
It is developed by RedHatAI, and it first shipped in 2019. The project is developed in the open on GitHub with 3.6k stars and 167 commits in the last 90 days. Among its 4 catalogued features are quantized weights, FP4 precision, and chat template.
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