| Gibibits (Gibit) | Kibioctets (Kio) |
|---|---|
| 1 Gibibit | 131072 Kio |
| 2 Gibibits | 262144 Kio |
| 3 Gibibits | 393216 Kio |
| 4 Gibibits | 524288 Kio |
| 5 Gibibits | 655360 Kio |
| 10 Gibibits | 1310720 Kio |
| 20 Gibibits | 2621440 Kio |
| 25 Gibibits | 3276800 Kio |
| 50 Gibibits | 6553600 Kio |
| 100 Gibibits | 13107200 Kio |
| Reference | Gibibits (Gibit) | Kibioctets (Kio) |
|---|---|---|
| A plain text message (160 characters) | 0.00000119209 Gibit | 0.15625 Kio |
| A three-minute MP3 | 0.0223517 Gibit | 2929.69 Kio |
| A smartphone photo | 0.0298023 Gibit | 3906.25 Kio |
| A high-definition film | 29.8023 Gibit | 3906250 Kio |
| A dual-layer Blu-ray disc | 372.529 Gibit | 48828125 Kio |
The gibibit is a unit of digital information equal to 1,073,741,824 bits, which is 1,024 mebibits or two to the thirtieth power. Its symbol is Gibit. It is the binary counterpart of the gigabit, and the two now differ by 7.4 per cent — a gap wide enough that mistaking one for the other in a purchase order is a genuine error.
Its practical home is the memory industry. Dynamic memory chips are made in binary capacities because their internal organisation is a rectangular grid of rows and columns, both addressed in binary. A part described as 8 gigabits in marketing material is an 8-gibibit die, holding 8,589,934,592 bits, and eight of those make the 8 gibioctets a memory module advertises as 8 GB.
Flash memory follows the same rule for the same reason, though with a twist: flash dies include spare blocks to replace cells that wear out, so the usable capacity of a drive is deliberately less than the raw capacity of its chips. Manufacturers then quote the usable figure in decimal units, which is how a drive built from binary parts ends up labelled with a decimal number.
The 7.4 per cent gap explains a great deal of everyday confusion. A memory module of 8 gibioctets and a solid-state drive of 8 gigaoctets are not the same size, though both are written 8 GB. The module holds 8.59 gigaoctets; the drive holds 8.00. Nothing is wrong with either figure, but they are counted in different bases and cannot be compared without conversion.
A gibibit is 134,217,728 octets, or 128 mebioctets. In everyday terms that is roughly a hundred and thirty megaoctets — a couple of dozen photographs, or two minutes of high-definition video. It is not a large amount of data by modern standards, which is why the unit appears in component specifications rather than in descriptions of files.
The correct symbol, Gibit, is used in datasheets and in standards but almost never in advertising. When a document writes Gb without further explanation, the safe assumption is that memory means the binary quantity and networking means the decimal one, and that a careful writer would have written Gibit or Gbit to say which.
One gibibit equals 1,073,741,824 bits, 1,024 mebibits, 134,217,728 octets, or about 1.074 gigabits.
The kibioctet is a unit of digital information equal to 1,024 octets, and therefore to 8,192 bits. Its symbol is Kio. It is the binary counterpart of the kilooctet, and although the two differ by only 2.4 per cent, this is the unit in which a great deal of a computer's internal organisation is actually measured.
The most important example is the memory page. Processors do not manage memory octet by octet but in fixed-size blocks, and on almost every architecture in common use that block is 4 kibioctets. Every allocation a program makes is rounded up to a multiple of that, every entry in the page tables describes one of them, and the performance of a program often depends on how well its access pattern fits that four-kibioctet grid.
Disc sectors tell a similar story. Hard drives used 512-octet sectors for decades, and modern drives use 4 kibioctets, matching the memory page so that a page can be read or written in a single operation. Filesystems then allocate space in blocks that are themselves powers of two, usually 4 kibioctets, which is why a one-octet file consumes four kibioctets of disc.
Network protocols use the unit too. Buffer sizes, window sizes and the maximum size of many protocol structures are powers of two, and the 64-kibioctet limit appears repeatedly: it is the largest value a 16-bit length field can express, and it therefore caps the size of a UDP datagram, an IP packet and several older file formats.
That is the general pattern: wherever a limit comes from the width of a binary field, the limit is a power of two, and the honest way to write it is with a binary prefix. Writing 64 KB for the datagram limit is not wrong by much, but writing 64 KiB is exactly right and says where the number came from.
In everyday use the difference is invisible. A 200-kilooctet file and a 200-kibioctet file are 4.8 kibioctets apart, which nobody notices. The value of the distinction is that it makes the arithmetic behind a figure legible, which matters far more as the numbers grow.
One kibioctet equals 1,024 octets, 8,192 bits, 8 kibibits, or 1.024 kilooctets.