DeepSeek
Summary
User reports a DeepSeek model at 2.25 bpw running at around 30-35 tokens/s on two RTX PRO 4000 Blackwell cards.
The machine is a Xeon W-2245 workstation with 256GB of DDR4-2666 ECC RAM in 8 x 32GB sticks. No engine, context length or KV cache setting is stated.
The speed is given only as a range, so no single figure is recorded.
Compare this run
Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.