Discover · piszczek.pl

67% more tokens per second from a tiny Blackwell

AI Economics Tools piszczek.pl

My RTX PRO 4000 Blackwell SFF went from 35.04 to 58.53 tokens per second on Qwen3.8 27B. Getting there took a 120 W power limit and faster GDDR7. Finding out which changes paid off took 158 benchmark requests. The more useful discovery: Qwen3.6 35B A3B responded very differently.

The first time I raised the power limit, the screen said 106 W. Under load, the GPU still drew about 70 W.

More ways to use this
Open on another device
Scan this QR code to open the same public page

Scan to open this page. Your saved notes and account access are not included.

Download QR code

Open the page link

In the piece

Keep going

Each of these is read from what this estate already kept: the feed a piece came through, the publisher behind it, the credits and topics the publisher printed. None of it is a recommendation, an identity or a record kept anywhere else.

More like this

Also from AI Economics Tools

  1. Looped Transformers Explained: How AI Thinks Longer Without Getting BiggerMichał Piszczek piszczek.pl
  2. The Average Is Free. Difference Is Not.Michał Piszczek piszczek.pl
  3. RSI AI Explained: What It Is and Where It Could LeadMichał Piszczek piszczek.pl
  4. Scarcity Never Dies. It Climbs.Michał Piszczek piszczek.pl
  5. Qwen3.8 27B at 256K: 50 TPS on a 24 GB GPUMichał Piszczek piszczek.pl
  6. DFlash Changes What Tokens per Second MeansMichał Piszczek piszczek.pl