Llama-4-Scout-17B-16E-Instruct-NVFP4

A Other model by nvidia

nvidia 14K downloads unknown Other
Frameworkssafetensors
TagsModel Optimizerllama4nvidiamodeloptquantizedFP4base_model:meta-llama/Llama-4-Scout-17B-16E-Instructbase_model:quantized:meta-llama/Llama-4-Scout-17B-16E-Instruct
Downloads
14K
License
unknown
Pipeline
Other
Author
nvidia

Run Llama-4-Scout-17B-16E-Instruct-NVFP4 locally on a Q4KM hard drive

Pre-loaded and ready to run. No download time. No configuration.

Shop Q4KM Drives

Pre-loaded AI models. Ready to run.

Skip the downloads. Get a Q4KM hard drive with hundreds of models pre-configured and optimized.

Shop Q4KM Hard Drives