smolmaxxing runs large models on old, low-power devices
What happened
smolmaxxing's work on running large language models on low-power and old devices was reported on the Hacker News front page on November 12, 2026. The devices named include a Xiaomi TV Box S (3rd Gen) and a 2013 iPad Air. The report says smolmaxxing uses custom kernels, memory optimization and streaming weights from storage to run models of up to 16B on these devices. It gives no inference speed, memory use or model names.
Written by AI from the coverage · updated 4 days ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageI'm making LLMs work on small and old devices
smolmaxxing 通过定制内核、内存优化和权重流式读取,让小米 TV Box S(3rd Gen)与 iPad Air(2013)运行最高 16B 模型。
Heat over time
Heat now 3·Comparable peak 10(Nov 13 01:00)·Comparable change over 24 hours -51%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.