Gigabyte to Exabit

Hard drive manufacturers measure 1 TB as 1,000,000,000,000 bytes (decimal). Windows displays storage in gibibytes (binary) but historically labelled them as "GB" — so 1,000,000,000,000 bytes ÷ 1,073,741,824 ≈ 931 GiB, which Windows displayed as "931 GB". macOS (since 10.6) correctly reports the same drive as "1 TB" using decimal GB. The drive is not lying; the OS was using a binary unit with a decimal label.

8 GB RAM is the current minimum for gaming; 16 GB is the recommended standard for most modern games at 1080p and 1440p; 32 GB benefits heavily multitasking systems or games with large open worlds. Memory-intensive tasks like video editing, 3D rendering, and running large language models locally typically require 32–64 GB or more.

A 4K movie in H.264 or H.265 encoding is typically 50–100 GB on Blu-ray; streaming services compress aggressively to 15–25 GB for 4K HDR content. Netflix's 4K streams average about 7 GB per hour; the downloaded version via the Netflix app for offline viewing is roughly 3–6 GB per hour at high quality settings.

1 GB of mobile data supports roughly: 2–3 hours of music streaming, 1 hour of HD video streaming, 2–3 hours of web browsing, or 30–60 minutes of video calling. Social media apps with autoplay video are heavy consumers — TikTok and Instagram Reels can use 300–600 MB per hour of active use.

AI model sizes vary enormously. GPT-2 (2019) is about 1.5 GB; Llama 2 7B is roughly 13 GB in float16 precision; Llama 2 70B is about 130 GB. GPT-4-class models are estimated at 500+ GB. Quantised (compressed) versions are smaller: a 4-bit quantised 7B model fits in about 4 GB, runnable on a modern laptop. Training requires far more — the training dataset, gradients, and optimizer states for a 70B model can occupy 1–2 TB of GPU memory across a cluster. The trend toward larger models is driving consumer GPU memory from 8 GB to 16–24 GB as a baseline for local AI inference.

One exabit = 10¹⁸ bits = 125,000 terabytes = 125 petabytes. If every person on Earth (8 billion people) each stored 15 GB of data — roughly a modern smartphone's photos and messages — the total would be about 120 exabytes, or about 960 exabits. The entire human genome is about 1.5 GB; sequencing every person on Earth would produce about 12 exabytes of data.

Cisco's annual internet traffic reports estimated global IP traffic at roughly 4.8 exabytes per day in 2022, rising about 20% per year. Expressed in bits, that's about 38 exabits per day or roughly 440 petabits per second continuously. Video streaming accounts for over 60% of total internet traffic volume.

Data gravity is the principle that massive datasets attract applications, services, and additional data toward them — rather than being moved to where processing occurs. At exabit scale, physically transferring data becomes impractical: moving 1 exabit over a 100 Gbps link takes 116 days. Instead, companies deploy compute resources alongside the data. This effect drives cloud concentration — once an organisation stores exabits in AWS or Azure, the cost and latency of moving that data elsewhere creates powerful vendor lock-in, shaping the economics of the entire cloud industry.

The Square Kilometer Array (SKA), under construction in Australia and South Africa, will be the world's largest radio telescope. Its thousands of antennas will collectively produce roughly 1 exabit of raw sensor data per day — more than the entire global internet traffic of the early 2000s. This data cannot be stored in full; instead, on-site supercomputers reduce it by a factor of ~10,000 in real time, keeping only scientifically relevant signals. The SKA illustrates how radio astronomy pushes data processing to extreme scales that rival commercial internet infrastructure.

At 1 Gbps (a fast home connection), downloading 1 exabit would take 1 billion seconds — about 31.7 years. At 1 Tbps (a high-end data center link), it would take 1 million seconds, or about 11.6 days. This illustrates why exabit-scale data movements require massively parallel infrastructure — no single link or device handles exabit transfers directly.