Models
Small Models That Run on One GPU, and What They Cost You
A quantized 27B model fits in 24 GB and handles most routine work. Throughput, not capability, is what actually limits it.
Models
14 articlesOngoing coverage of the major model families and how they're evolving release to release.
14 articles
-
-
ModelsMillion-Token Context Windows: A Ceiling, Not a Budget
Uneven attention, rate limits below the advertised window, and linear cost on every call. Useful — and frequently misapplied.