NVIDIA-Nemotron-Nano-9B-v2-FP8 is a 9 billion parameter language model published on Hugging Face. It provides optimized FP8 weights for efficient inference while supporting advanced features such as tool calling and custom chat templates. The model is intended for developers who want to run or fine-tune capable open-weight LLMs either locally or through inference providers.
NVIDIA Nemotron Nano 9B is a Foundation models & chat product. It focuses on accessing and running a high-performance, quantized open-weight language model locally or via API. It is built as an open-source project for developers. NVIDIA Nemotron Nano 9B is open source under the Open Source license. The product ships for the command line and API.
Behind NVIDIA Nemotron Nano 9B is NVIDIA, based in the United States, and the product first shipped in 2025. Key capabilities include model weights, chat template, and tool calling. It exposes integrations via a public API.
Latest indexed changes and source events
nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8 verified by the PulseGate indexer
Other apps tracked under the same category.
