RTX Pro 5000 Blackwell Ollama: Qwen2.5 32B eval rate (Computingforgeeks)
42.9 tok/s (eval rate, per-request)
Fields
id
benchmarks/cfgk-pro5000-ollama-qwen25-32b-evalMetric
decode_tok_s
Value
42.9
Unit
tok/s (eval rate, per-request)
Model
qwen2.5:32b
Methodology
Computingforgeeks single-card Ollama comparison, published 2026-09-11, run on Ubuntu 26.04 with NVIDIA driver 580 and Ollama 0.11. Each card tested alone. Prompt is a fixed ~2,000-token document summarization request, output capped at 500 tokens, three runs averaged. The reported eval rate is decode tokens/s, per request, batch size 1, not an aggregate. Quantization is whatever `ollama pull` ships for the tag (page does not name the GGUF quant). RTX Pro 5000 Blackwell here is the 48 GB GDDR7 ECC card (32 GB model footprint fits); the 72 GB SKU is a different accelerator and was not tested.
Measured by
third_party
Reproducible
yes
notes
Table cell Pro 5000 / qwen2.5:32b eval 42.9 tok/s, prompt eval 1,920 tok/s, VRAM 19.4 GB. Agrees with the Database Mart eval of 42.92 tok/s on the same Ollama tag to well inside run noise, on a different host and an older Ollama (0.11 vs 0.12.3).
Notes
Table cell Pro 5000 / qwen2.5:32b eval 42.9 tok/s, prompt eval 1,920 tok/s, VRAM 19.4 GB. Agrees with the Database Mart eval of 42.92 tok/s on the same Ollama tag to well inside run noise, on a different host and an older Ollama (0.11 vs 0.12.3).