DEEPSEEK / 2026

DeepSeek V4 Pro

A frontier-scale model combining fine-grained sparse experts with a million-token context for agentic work.

TOTAL PARAMETERS1.6T
ACTIVE / TOKEN49B
PINNED ARTIFACT864.7 GB
MAX CONTEXT1M

DECISION BRIEF

Frontier open reasoning

The pinned artifact contains 864.7 GB of tensors. Sparse token compute does not remove the need to place the full sharded checkpoint and validate runtime support.

WEIGHTSOpen weights

Publicly available checkpoints; verify terms before commercial deployment.

LICENSEUnverified in registry

Unknown remains explicit until the exact checkpoint license is verified and sourced.

EVIDENCEPrimary source

Architecture values are linked to the publishing organization.

ARCHITECTURE

Compute is sparse. Residency is not.

The pinned artifact contains 864.7 GB of tensors. Sparse token compute does not remove the need to place the full sharded checkpoint and validate runtime support.

Expert topology: 384 / top-6. The active-parameter count approximates token-level compute; it does not determine checkpoint memory, KV-cache demand, expert placement, or interconnect pressure.

PRIMARY SOURCE

DeepSeek V4 Pro release

Inspect evidence
PINNED ARTIFACT

deepseek-ai/DeepSeek-V4-Pro@b5968e9190ef · 864.7 GB

Open manifest

NEXT ACTION

Test the workload, not the headline.

Start with checkpoint residency, then layer in context, concurrency, runtime overhead, topology, and resilience.

Build an assurance plan