How much memory does Kimi K3 need in Q4?

Kimi K3 has 2800 billion parameters. The Q4 format decides how much memory is needed to load them.

Short answer. In Q4, the weights of Kimi K3 take about 1,610 GB including the runtime margin. 2 of the 8 platforms in the catalogue have enough memory.

How is this footprint calculated?

Kimi K3 totals 2800 billion parameters. The Q4 format takes 0.5 byte per parameter. The product gives the weights, to which a 15% runtime margin is added for activations and buffers. The attention cache is not included: it grows with context and concurrency.

What does the format change?

Q4 brings block quantisation, broadly supported.

Format	Weights in memory	Compatible platforms
FP16	6,440 GB	1
FP8	3,220 GB	1
NVFP4	1,610 GB	2
Q4	1,610 GB	2

Which platforms qualify?

See the Kimi K3 fact sheet.

How much memory for Kimi K3 in Q4?

About 1,610 GB for the weights, excluding the attention cache.

Which format should I choose for Kimi K3?

Q4 brings block quantisation, broadly supported. The most precise format that fits the target machine remains the best choice.

Method

Parameter counts and memory figures come from the site fact sheets. Memory footprints are calculated, not measured: a reading on real hardware may differ depending on the engine and the exact weight format. Prices are indicative and not contractual.