low-power inference mode.
$71 · Drop 01 · 1000 made
Quantized to double espresso precision. Latency reduced, hallucinations preserved.
An AI & machine-learning in-joke cap from from_llmceo_with_love — wearable AI & machine-learning merch for machine learning engineers, AI engineers, LLM developers. Riffs on quantization, model inference, low latency.
- Material
- Washed cotton-twill
- Composition
- 100% cotton
- Colour
- Washed black
- Size
- One size, adjustable strap.
- Care
- Easy care; holds its shape and resists static.