The lab
Small demos you can run in your browser
Each one shows how something behaves, and where I measured it on my own machines, the number links to the file. For who I am and the work behind this, start at coinupbtc.com.
The bench
Four demos
-
AI serving
Speculative decoding
A small model drafts the next few words and the big model checks them all in one pass. Move the sliders to see when drafting saves time and when it costs time.
Measured On a copy-heavy refactor, 34.33 → 74.48 tokens per second. Report §9
Open the demo -
Capacity planning
Memory packer
Pick one, two or three DGX Spark machines and the models you want to run, and see whether they fit. Each machine has its own memory; two machines are not one big pool.
Measured 121 GiB per machine; the video model holds 89.42 GiB on one after loading. Results
Open the demo -
Performance
Render cost
Selecting one row used to rebuild every row in the list. This runs the bug and the fix side by side and times both in your browser.
Measured In the real app: 13 s before the fix, 7.5 ms after, at 516 records.
Open the demo -
Measurement
Moiré bench
Two grids that almost line up. The pattern you see is where they disagree. A vernier caliper reads small differences the same way: a tiny mismatch between two scales becomes easy to see.
Try Move one layer’s spacing by a single 1% step and watch the pattern shift a long way.
Open the demo
Notes
Write-ups
- Hermes Agent on two DGX Sparks
Four months of Nous Research's agent on a local DeepSeek-V4.1 pair: what runs, the three engine patches now upstream, and four lessons from running Hermes all day, checked against today's code.
- A 90-second stall, fixed
One long prompt stalled every live conversation on a two-machine setup, for two minutes on mine. I wrote the patch and it was merged upstream. The bug, the fix, and who measured what.