>>
Run Kimi-K2.5 on Lium
Moonshot AI · Vision and text · 1T parameters · 595.2 GB 5-bit weights · released 2026-01-01
It needs about 715 GB of VRAM. The cheapest setup that runs it is 8x RTX PRO 6000 Server (768 GB), from $14.40 per hour, billed per second.
Other GPUs that run it
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve moonshotai/Kimi-K2.5:
vllm serve moonshotai/Kimi-K2.5 --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does Kimi-K2.5 need?
About 595.2 GB for the released 5-bit weights, so plan on 715 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-K2.5?
8x RTX PRO 6000 Server (768 GB). On Lium that setup costs from $14.40 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt