Skip to content
AI & Machine Learning Medium #scaling#parameters#flops

Parameter Count vs Compute

Params, layers, and FLOPs scale together. Where AlexNet, ResNet, GPT-3, GPT-4 sit on the curve.

A free, animated parameter count vs compute you can read here or embed on any website, from Scrollchart.

Parameter Count vs Compute

Parameter Count vs Training ComputeLog-log: FLOPs scale roughly as params squared (6 FLOPs per param per forward pass)10^510^610^710^810^910^1010^1110^12Parameter count10^810^1010^1210^1410^1610^1810^2010^2210^24Training FLOPs~6 FLOPs / param trendKey ratios6 FLOPs / paramper fwd pass (matmul)3x fwd for bwdgrad + activationsChinchilla opt.20 tokens / paramGPT-3: 175B params3.14 x 10^23 FLOPsCNN / BERTGPT familyEach decade of params requires ~2 decades more compute (slope = 2 on log-log axes)

Param count vs FLOPs on log-log axes. Models from LeNet to GPT-4 scale plotted. Trend line and the compute-per-param ratio annotated.

Good for

  • AI scaling law explainers connecting parameter count, data, and compute for non-technical audiences
  • ML infrastructure cost articles estimating training budgets from model size
  • Deep learning curriculum visualizing why architecture efficiency (MobileNet, ViT) matters at scale

Source & accuracy

This parameter count vs compute is an editorial illustration built to represent the concept accurately. Where it shows figures, they are typical or representative values chosen to make the relationship clear, not a single underlying dataset. The diagram and its explainer are reviewed and maintained centrally, and updated over time as understanding improves.

Tracking the growth of AI models

Parameter counts have grown exponentially across AI milestones. AlexNet (2012) had 60 million parameters and marked the start of the deep learning revolution. ResNet-50 (2015) had 25 million. VGG-19 (2014) had 144 million. GPT-1 (2018) introduced a 117 million parameter language model. GPT-2 (2019) jumped to 1.5 billion. GPT-3 (2020) reached 175 billion. Modern models like GPT-4 and Llama 2 are estimated in the hundreds of billions to low trillions. This growth reflects increasing compute availability and the discovery that scale consistently improves performance across tasks. Scaling laws predict this growth: loss improves predictably with parameters, and this property persists across orders of magnitude.

The relationship between size and capability

Larger models are not just better versions of smaller ones; they exhibit emergent behaviors. GPT-1 was a language model; GPT-3 became a general-purpose few-shot learner. Parameter count correlates strongly with downstream capability on diverse benchmarks. However, scaling laws also show diminishing returns: doubling parameters does not double capability. The tradeoff is compute cost: training GPT-3 required many times the FLOPs of training BERT, even adjusting for dataset size. Modern research focuses on efficiency: Chinchilla and subsequent work showed that prior models were undertrained relative to their size, and more careful allocation of parameters and data yields better results. The field is shifting toward efficiency alongside scale.

Embed this diagram

Add this animated parameter count vs compute to your own site. Copy one line of HTML, or use the embed builder for theme and sizing options.

Reference

What this is
A free, embeddable, animated parameter count vs compute for any website.
Who uses it
AI/ML blogs, Science popularizers.
How to embed
Copy one line of HTML. No signup. No watermark. Works in WordPress, Webflow, Ghost, Substack, plain HTML.
File size
iframe embed, ~80 KB gzipped (loads on demand, does not block your page paint).
License
Free forever. Editorial explainer text included; updated centrally over time.

Embed format options

Copy the universal HTML snippet, the WordPress shortcode, or an iframe fallback - see the WordPress plugin page for details. Any format keeps the same Core Web Vitals profile and the same explainer text.

Embed snippet
<div data-scrollchart="parameter-count-scaling" data-scrollchart-v="1"></div>
<script src="https://scrollchart.com/embed.js" async></script>

Frequently asked questions

Where can I get a free animated "Parameter Count vs Compute" for my website?
Scrollchart provides "Parameter Count vs Compute" as a free, embeddable animated diagram you can add to any website with one line of HTML. No signup is required and there is no watermark. The diagram and its explainer text are served from scrollchart.com, so the embed stays current without any maintenance on your end.
How do I embed a parameter count vs compute in a developer or tech blog?
Copy the one-line snippet from the Scrollchart diagram page and paste it into your post HTML. It works in any static site generator, CMS, or hand-coded HTML page. The embed is a thin loader, not an iframe, so the content is fully in your DOM.