How should a team disclose MoE model size for honest latency and cost comparisons?
How should a team disclose MoE model size for honest latency and cost comparisons?
Disclose both total params (memory) and active params per token (compute), plus top-k and expert count, a single headline number misleads buyers and infra teams alike.
A MoE model is like a hospital with eight specialist departments but only two treat each patient. Quoting 'eight departments' tells you building size (memory); quoting 'two doctors per patient' tells you wait time (compute). Honest reporting gives both numbers.
Detailed answer & concept explanation~6 min readEverything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
Everything important, quickly.
6 min: dual-number spec + stakeholder mapping + dishonest reporting traps + model card template.
Real products, models, and research that use this idea.
- DeepSeek-V3 model card reports total and active parameters separately.
- Mistral publishes Mixtral as ~47B total with ~13B active inference behavior.
- Cloud API pricing for MoE models often references active FLOPs, not total capacity.
What an interviewer would ask next. Try answering before peeking at the approach.
Don't say thisRed flags and common mistakes that signal junior thinking. Click to expand.
Red flags and common mistakes that signal junior thinking. Click to expand.
Publishing only total params for marketing or only active params to hide memory requirements.
The night-before-the-interview bullets. Scan these on the way to the call.
Primary sources. Skim if you want the original framing.
Same topic, related formats. Practice these next.