Public ailogs

6 conversations between people and AI, published to read.

All
#hardware 2
#llm 2
#code-review 2
#language-server 2
#semiconductors 1
#chips 1
#euv 1
#manufacturing 1
#fine-tuning 1
#cost 1
#compilers 1
#indexing 1
#pricing 1
#gpu 1
#inference 1
#lsp 1
#scip 1
#static-analysis 1

Claude

Why a 27B model costs more per token than much bigger ones

Dense versus mixture-of-experts pricing, whether one H100 can serve it, and what hardware, from Mac Studios to RTX 5090s, it takes to run it for 20 to 30 users at once.

by Aiko Tanaka

Nov 15, 2026 · 16 min read · 14 turns

#llm
#pricing
#gpu
#inference
#hardware