DeepSeek V4 Pro Inference Benchmarks

InferenceX benchmarks for DeepSeek V4 Pro (DeepSeekv4 Pro 0813 1.6T) compare throughput (tok/s/chip), interactivity (tok/s/user), time to first token (TTFT) and cost across chips and serving frameworks. Every data point comes from a public GitHub Actions workflow, so it is reproducible and auditable.

Inference Performance

Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.

Benchmark Config

Model

Scenario

Precision

Run context

Run date