Running Kimi K2.7 Code on B200 SXM

Kimi K2.7 Code has 1000 billion parameters. B200 SXM offers 1,440 GB of HBM3e across 8 GPUs memory. This page puts the two side by side.

Short answer. Kimi K2.7 Code fits comfortably on B200 SXM. In FP8, its weights take about 1,150 GB of the 1,440 GB available, leaving 290 GB for the attention cache and concurrency.

How much memory does Kimi K2.7 Code need?

Weights take the parameter count multiplied by the format size, plus a 15% runtime margin for activations and buffers. The attention cache sits on top: it grows with context length and with the number of concurrent requests, so it is sized case by case.

Format	Weights in memory	On this machine	What the format costs
FP16	2,300 GB	does not fit	full precision, the quality reference
FP8	1,150 GB	tight	negligible loss on most tasks
NVFP4	575 GB	fits	Blackwell format, native FP4 compute
Q4	575 GB	fits	block quantisation, broadly supported

What is left to serve requests?

Kimi K2.7 Code fits comfortably on B200 SXM. In FP8, its weights take about 1,150 GB of the 1,440 GB available, leaving 290 GB for the attention cache and concurrency. The remaining margin decides how many concurrent requests and how much context the machine sustains. A margin below a quarter of memory forces a limit on context or on concurrency.

Where else can Kimi K2.7 Code run?

See the Kimi K2.7 Code and B200 SXM fact sheets.

How much memory does Kimi K2.7 Code need?

In FP8, weights take about 1,150 GB including the runtime margin. The attention cache sits on top and depends on context.

Does Kimi K2.7 Code fit on B200 SXM?

Kimi K2.7 Code fits comfortably on B200 SXM. In FP8, its weights take about 1,150 GB of the 1,440 GB available, leaving 290 GB for the attention cache and concurrency.

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.