DeepSeek-V4-Flash | NVIDIA NGC

Deepseek AI

DeepSeek-V4-Flash

Container

Deepseek AI

DeepSeek-V4-Flash

The DeepSeek-V4-Flash NIM Container is a deployable inference container for serving DeepSeek-V4-Flash, a third-party sparse Mixture-of-Experts language model optimized for fast coding, reasoning, long-context, and agentic workflows

NVIDIA NIM

NIM MetadataTo verify your workspace, run the Verify CLI locally and compare the generated hash with the NGC-published hash shown here. Learn more in the NVIDIA Documentation.Get detailed NIM model metadata, including properties, deployment, and configuration, via the NIM Metadata API.

		Engine					Actions
H20-3e	fp8	sglang	4	—	—	—	Copy NIM CLI Verification
—	fp8	sglang	8	—	—	—	Copy NIM CLI Verification
H200	fp8	sglang	4	—	—	—	Copy NIM CLI Verification
H100	fp8	sglang	8	—	—	—	Copy NIM CLI Verification
B200	fp8	sglang	4	—	—	—	Copy NIM CLI Verification