HOSTKEY: RTX PRO 5000 72GB Blackwell, deepseek-r1:14b, Ollama, avg decode
67.71 tok/s
Fields
id
benchmarks/hostkey-rtxpro5000-72gb-deepseek-r1-14b-ollama-decodeMetric
decode_tok_s
Value
67.71
Unit
tok/s
Model
DeepSeek R1 14B
Methodology
Per-request decode tok/s, one request at a time (the table reports a single average tokens/sec, not an aggregate across concurrent requests). HOSTKEY own-hardware test, article dated 2026-08-09, of one NVIDIA RTX PRO 5000 Blackwell 72 GB (PCI id 10de:2bb3, double-sided memory) in a Ryzen 9 7950X host, 128 GB DDR5, Ubuntu 24.04, Ollama. Model is the Ollama tag deepseek-r1:14b. DeepSeek-R1-Distill-Qwen-14B pulled as the Ollama tag deepseek-r1:14b. Ollama version, the GGUF quantization tag, the prompt length and the number of generated tokens are NOT stated on the page, so format_id is null and no prompt or output length is asserted. The companion R9700 article (hostkey.com/blog/142) describes the same harness: a custom Ollama test reporting average tokens/sec, max context, load time and generation time.
Measured by
third_party
Reproducible
no
notes
First published measurement found for nvidia-rtx-pro-5000-72gb-blackwell, which previously had zero benchmark records. The page also prints a max-context column and a load-time column; those are not filed because neither is a metric this record type measures. Do not read this number as comparable to the Hardware Corner llama-bench tables for the 48 GB SKU: different engine, unstated quant, unstated context depth.
Notes
First published measurement found for nvidia-rtx-pro-5000-72gb-blackwell, which previously had zero benchmark records. The page also prints a max-context column and a load-time column; those are not filed because neither is a metric this record type measures. Do not read this number as comparable to the Hardware Corner llama-bench tables for the 48 GB SKU: different engine, unstated quant, unstated context depth.