Kimi K2.7 Code

1,000 billion parameters · Modified MIT license · moonshotai/Kimi-K2.7-Code

How much GPU memory does this need?

required GB = parameters (billions) × 1 GB, plus 20% working room

1,000 × 1 GB = 1,000 GB
1,000 GB × 1.2 = 1,200.0 GB required

GPU memory is the "workspace" a graphics card uses to hold an AI model while it runs. If a model is bigger than the available memory, it simply will not fit — like trying to fit a large book on a shelf that's too small. More in the wiki →

Minimum setup to run Kimi K2.7 Code

NVIDIA DGX B200

1x NVIDIA DGX B200

  • 1,440 GB combined GPU memory (needs ≥ 1,200.0 GB — meets the requirement)
  • 14,300 W combined power draw
  • $500,000 total price

That's as much power as about 11.9 average homes, and about 3.81 electric-car batteries of energy per day of running. An average home draws roughly 1,200 watts around the clock. This compares a build's power draw to that baseline. More in the wiki →