Local AI, timed on machines I own
I run AI models at home on hardware I bought myself, and I publish what I measure: which model, on which machine, how fast, and how it was timed.
The benchmarks so far
| Machine | Model | Writing code | Reading (prefill) | Tested |
|---|---|---|---|---|
| Four DGX Sparksgraphics chips capped at 2,200MHz to cut power use | GLM 5.3 FlashNVFP4 at 4 bits, dense layers at 8 | 104.1 tok/s | 3,159 tok/s | 11 Oct 2026 |
| Two DGX Sparksgraphics chips capped at 2,200MHz to cut power use | Qwen 3.8 27BNVFP4 at 4 bits | 44.7 tok/s | 2,034 tok/s | 11 Oct 2026 |
| One DGX Sparkgraphics chips capped at 2,200MHz to cut power use | Qwen 3.8 27BNVFP4 at 4 bits | 26.7 tok/s | 1,188 tok/s | 11 Oct 2026 |
| RTX 4090 desktop | Qwen 3.8 27BQ4_K_M, GGUF | 62.4 tok/s | 1,994 tok/s | 11 Oct 2026 |
| HP ZBook Ultra G1aStrix Halo laptop, Ryzen AI Max+ 395, 64GB | Qwen 3.8 27BQ4_K_M, GGUF | 23.5 tok/s | 194 tok/s | 11 Oct 2026 |
One user, the model's thinking switched off, the same prompts and the same script on each machine. My Sparks would run a little faster than the figures on this page. I cap their graphics chips at 2,200MHz, against about 2,400 uncapped, to cut their power use. When I tested the cap on one box in August, writing speed stayed within 1 per cent, reading was 2 to 4 per cent slower, and the chip's peak power fell from 55.5W to 43.3W. Every figure, the runs with thinking on, the hardware and how I test.
The weekly video
Local AI, This Week is a short video each week on what changed for people who run AI models at home. These are the latest episodes, and all of them are on the YouTube channel.
- RTX Spark Laptop vs DGX Spark: Buy or Wait?, 10 October 2026
- $4,999 DGX Spark vs M5 Ultra Mac Studio, 3 October 2026
- Are 4x M5 Ultra Mac Studios faster at AI than 1?, 28 September 2026
- DeepSeek V4.1 Flash on 2 DGX Sparks!, 19 September 2026
What is coming to this site
- The stories from each episode, with the source of every number in them.
- A page for each machine: what it costs, what it runs and how fast.
- A corrections page. If a figure looks wrong, tell me under the latest video and I will run it again.