NVIDIA Nemotron Nano 12B v2 VL FP8 is an FP8-quantized, open-weight vision-language model distributed through Hugging Face. Developers and researchers can download and run it locally or deploy it with compatible inference tooling for multimodal text and image tasks.
In the Multimodal & vision space, NVIDIA Nemotron Nano 12B V2 VL takes a focused approach. It focuses on running a multimodal language model locally for text, image, and code tasks. It is built as an open-source project for AI developers and researchers. NVIDIA Nemotron Nano 12B V2 VL is open source under the Apache-2.0 license. It runs on the web, the command line, and API, and it can be self-hosted.
NVIDIA builds and maintains NVIDIA Nemotron Nano 12B V2 VL, and it first shipped in 2024. Development happens publicly on GitHub with 3.5k stars and 334 commits in the last 90 days. PulseGate's similarity index places it among 12 comparable projects. Key capabilities include vision-language understanding, text generation, and image understanding.
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