Task
Text Generation
D
nvidia/DeepSeek-V4-Flash-NVFP4
Text Generation·nvidia· 359.7K· 55
Model Optimizer
mit
Text Generation
166.7B params
base_model:deepseek-ai/DeepSeek-V4-Flashbase_model:quantized:deepseek-ai/DeepSeek-V4-Flash
Description: The NVIDIA DeepSeek-V4-Flash-NVFP4 model is a quantized version of DeepSeek AI's DeepSeek-V4-Flash model, an autoregressive Mixture-of-Experts language model that uses an optimized Transformer architecture with hybrid attention (Compressed Sparse Attention and Heavily Compressed Attention) and Manifold-Constrained Hyper-Connections. For more information, refer to the DeepSeek-V4-Flash
# pull & run locally
pip install mlforge-sdk && mlforge pull nvidia/DeepSeek-V4-Flash-NVFP4
pip install mlforge-sdk && mlforge pull nvidia/DeepSeek-V4-Flash-NVFP4
Model details
Provider
nvidia
Framework
Model Optimizer
Parameters
166.7B
Size
164 GB
License
mit
Downloads
359.7K
Likes
55
Updated
2026-06-15
About nvidia/DeepSeek-V4-Flash-NVFP4
Description: The NVIDIA DeepSeek-V4-Flash-NVFP4 model is a quantized version of DeepSeek AI's DeepSeek-V4-Flash model, an autoregressive Mixture-of-Experts language model that uses an optimized Transformer architecture with hybrid attention (Compressed Sparse Attention and Heavily Compressed Attention) and Manifold-Constrained Hyper-Connections. For more information, refer to the DeepSeek-V4-Flash model card. The NVIDIA DeepSeek-V4-Flash-NVFP4 model is quantized with Model Optimizer.