| Kibibits per second (Kibit/s) | Pebibits per second (Pibit/s) |
|---|---|
| 1 Kibibit per second | 9.09494701773 × 10-13 Pibit/s |
| 2 Kibibits per second | 1.81898940355 × 10-12 Pibit/s |
| 3 Kibibits per second | 2.72848410532 × 10-12 Pibit/s |
| 4 Kibibits per second | 3.63797880709 × 10-12 Pibit/s |
| 5 Kibibits per second | 4.54747350886 × 10-12 Pibit/s |
| 10 Kibibits per second | 9.09494701773 × 10-12 Pibit/s |
| 20 Kibibits per second | 1.81898940355 × 10-11 Pibit/s |
| 25 Kibibits per second | 2.27373675443 × 10-11 Pibit/s |
| 50 Kibibits per second | 4.54747350886 × 10-11 Pibit/s |
| 100 Kibibits per second | 9.09494701773 × 10-11 Pibit/s |
| Reference | Kibibits per second (Kibit/s) | Pebibits per second (Pibit/s) |
|---|---|---|
| A dial-up modem | 54.6875 Kibit/s | 4.9738 × 10-11 Pibit/s |
| Typical home broadband | 97656.2 Kibit/s | 0.0000000888178 Pibit/s |
| Gigabit Ethernet | 976562 Kibit/s | 0.000000888178 Pibit/s |
| Streaming a 4K film | 24414.1 Kibit/s | 0.0000000222045 Pibit/s |
The kibibit per second is a unit of data transfer rate equal to 1,024 bits per second. Its symbol is Kibit/s. It is the binary counterpart of the kilobit per second, and it is the least used member of an already unusual family, because transfer rates are one of the few places in computing where the decimal convention has always been unambiguous.
Networking has counted in true thousands from the beginning. A modem rated at 56 kilobits per second meant fifty-six thousand, not fifty-seven thousand three hundred and forty-four. The reason is that a transmission rate is set by a clock, and clocks are specified in decimal frequencies: a link running at ten million symbols per second carries a decimal number of bits, not a power of two.
The binary prefixes exist for quantities, not for rates, because quantities of storage are organised in powers of two while time is not. There is no natural reason for a rate to be a power of two, and consequently no reason for a rate unit to need a binary prefix. Where one appears, it is almost always because a program divided a binary file size by a duration.
That is exactly where the kibibit per second does turn up. A tool that measures a transfer by counting kibioctets and dividing by seconds produces a rate in kibioctets per second, and multiplying by eight gives kibibits per second. The unit is a consequence of the arithmetic rather than a description of the channel.
For scale, a kibibit per second is 128 octets per second, and the difference from a kilobit per second is 2.4 per cent — smaller than the measurement error of almost any real throughput test. At this level the distinction is technically correct and practically invisible, which is a fair description of the whole binary prefix system at its lower end.
The unit is properly defined and a converter must handle it, because the IEC series applies to every unit without exception. Whether anyone writes it is a separate question from whether it means something definite, and it does.
One kibibit per second equals 1,024 bits per second, 128 octets per second, or 1.024 kilobits per second.
The pebibit per second is a unit of data transfer rate equal to 1,024 tebibits per second, which is two to the fiftieth power bits per second. Its symbol is Pibit/s. It is the binary counterpart of the petabit per second, and the two differ by 12.6 per cent.
No deployed system runs at this rate, and the unit therefore describes either an aggregate or a laboratory result. Optical transmission records set on single fibres reach a petabit per second, and the binary figure for the same experiment is 12.6 per cent lower — a difference that matters when comparing results between papers that use different conventions.
Where the unit is genuinely appropriate is in describing structures built from powers of two. The total switching capacity of a very large network fabric, built from ports and buffers that are all binary, is a binary quantity divided by time, and reporting it in decimal units discards the arithmetic that produced it. The same applies to the summed memory bandwidth of a machine whose channel count is a power of two.
In octets a pebibit per second is 140,737,488,355,328, which is 128 tebioctets per second. That is the storage of a thousand large consumer drives moved every second, and it exists only as a total across many thousands of parallel paths inside a single facility.
The size of the discrepancy at this level is the argument for the whole IEC series in miniature. What began as a harmless 2.4 per cent at the kibibit is now an eighth, and it compounds by 2.4 per cent at every further step. A convention that was acceptable for small numbers becomes untenable for large ones, and the point of the binary prefixes is to make the distinction visible before that happens.
For a converter, the arithmetic is unremarkable: multiply or divide by 1,024 the appropriate number of times, and by eight to reach octets. What matters is that the tool does not silently substitute the decimal unit when it sees a value it cannot label precisely.
One pebibit per second equals 1,024 tebibits per second, 140,737,488,355,328 octets per second, or about 1.126 petabits per second.