RTX PRO 5000 Blackwell Ollama: gpt-oss 20B eval rate (Database Mart)

Database Mart hosted GPU-server benchmark of one NVIDIA RTX Pro 5000 Blackwell Server Edition (48 GB GDDR7 ECC, 300 W, PCIe 5.0 x16, driver 580.65.06, CUDA 13.0). Engine is Ollama 0.12.3 via the Ollama API (llama.cpp backend; Ollama build commit not printed). Quantization is the default Ollama pull for each tag, which the report labels INT4 and does not further specify (not asserted as Q4_K_M). Prompt is fixed at 2048 tokens (fixed-length text file, 50 repetitions); output length is not stated. The published column is eval rate (tokens/s), which is decode, per request, batch size 1, NOT an aggregate across concurrent requests. prompt eval rate is a separate column and is not recorded here. Card is the 48 GB Server Edition, not the 72 GB workstation SKU.

Table row gpt-oss:20b, 14 GB model, load 4.88 s, prompt eval 5033.97 tok/s, eval 169.41 tok/s. Highest eval rate in the 20-model sweep. INT4 as pulled by Ollama; exact GGUF quant not printed.