This is an FP8 quantized checkpoint of NVIDIA's Llama-4 Scout 17B model with 16 experts. It is released under the NVIDIA Open Model License and supports commercial use and derivative works. The model is designed for instruction following and general language tasks.
In the Foundation models & chat space, Llama 4 Scout 17B 16E Instruct takes a focused approach. It focuses on running large-scale instruction-tuned language models efficiently with reduced precision on compatible hardware. It is built as an open-source project for developers. Llama 4 Scout 17B 16E Instruct is open source under the Open Source license. The product ships for the web and API.
Behind Llama 4 Scout 17B 16E Instruct is NVIDIA, based in the United States, and the product first shipped in 2023. Development happens publicly on GitHub with 14.2k stars and 1.9k commits in the last 90 days. Key capabilities include mixture of Experts, Instruction Tuning, and Quantized Inference.
Latest indexed changes and source events
nvidia/Llama-4-Scout-17B-16E-Instruct-FP8 verified by the PulseGate indexer
Other apps tracked under the same category.
