>>
Run Kimi-K2-Instruct on Lium
Moonshot AI · Text generation · 1T parameters · 1029.2 GB FP8 weights · released 2025-07-11
It needs about 1236 GB of VRAM. The cheapest setup that runs it is 8x B300 SXM6 (2304 GB), from $32.00 per hour, billed per second.
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve moonshotai/Kimi-K2-Instruct:
vllm serve moonshotai/Kimi-K2-Instruct --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does Kimi-K2-Instruct need?
About 1029.2 GB for the released FP8 weights, so plan on 1236 GB with room for activations and KV cache at a short context. Longer contexts and bigger batches need more.
What GPU should I rent to run Kimi-K2-Instruct?
8x B300 SXM6 (2304 GB). On Lium that setup costs from $32.00 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt