nvidia
/

DeepSeek-V4-Pro-NVFP4

Text Generation

Model Optimizer

8-bit precision

Model card Files Files and versions

DeepSeek-V4-Pro-NVFP4 / hf_quant_config.json

Commit History

Un-quantize MTP block (revert to native precision)

9e7e88e
verified

jingyux-nv commited on 2 days ago

Add files using upload-large-folder tool

bc21101
verified

jingyux-nv commited on 17 days ago