RadixArk/Qwen3.8-Flash-Next-NVFP4 is an open model checkpoint hosted on Hugging Face. It provides a quantised Qwen model intended for developers and ML engineers running efficient local or self-hosted inference, including multimodal inputs.
In the Quantised & converted weights space, Qwen3.8 Flash Next takes a focused approach. It focuses on running a smaller, quantised Qwen model for efficient AI inference. It is built as an open-source project for machine learning engineers and developers. Qwen3.8 Flash Next is open source under the Apache-2.0 license. It ships for the web, the command line, and API, and it can be self-hosted.
It is developed by RadixArk, and it first shipped in 2024. The project is developed in the open on GitHub with 3.6k stars and 334 commits in the last 90 days. Among its 5 catalogued features are quantised weights, vision input, and text generation.
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