GPT-OSS-20B-NPU2 is an open-weight language model repository hosted on Hugging Face, adapted for neural processing unit inference. It provides model files and configuration for developers and researchers running local text and code generation workloads.
In the Foundation models & chat space, GPT OSS 20B NPU2 takes a focused approach. It focuses on running an open-weight language model efficiently on compatible neural processing hardware. GPT OSS 20B NPU2 is an open-source project aimed at AI developers and researchers. GPT OSS 20B NPU2 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.
FastFlowLM builds and maintains GPT OSS 20B NPU2, and it first shipped in 2025. The project is developed in the open on GitHub with 4.5k stars. Key capabilities include text generation, code generation, and tool calling.
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