DeepSeek V4 Pro 1600B (49B active)

on NVIDIA RTX PRO 6000 Max-Q · ktransformers · 65,536 ctx

May 16, 2026

Throughput

7.1 t/s gen · 46.2 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

System RAM

1152 GB

VRAM reported

96 GB

Summary

User benchmarks at various context depths on an Epyc 9374F. GPU VRAM usage is 90815MiB/97887MiB and RAM usage is 907.5GB/1152GB. Power draw is about 100W prefill and 150W token generation for the GPU, and about 400W for the CPU and motherboard. The original model files are used with no conversion.

View source ↗