Equation 5 · Part 1 · Comparing the Main Approaches to AI Inference Economics
Symbol N_total
What this part means
otal is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Its job in the formula
otal is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Full expression→Symbol N_total→Article meaning
The passage around this formula
for a dense model with parameters compared against an MoE model activating of its parameters per token. What this ratio hides is exactly what a compute-only comparison always hides: memory. Serving an MoE model requires holding all parameters resident — on one device or, more often, sharded across several with communication between them…
Learn the underlying idea
A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.
Open the illustrated subscripts: which member of a family? guide →
See this notation across published equations →
Sources cited in the article section
- [12] Mixtral of Experts ↗
- [11] DeepSeek-V3 Technical Report ↗
- [13] Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity ↗
- [8] Pricing ↗
These citations provide research context; check each source for the exact claim it supports.