>>
Run DeepSeek-V3.2 on Lium
DeepSeek · Text generation · 685.4B parameters · 689.5 GB FP8 weights · released 2025-12-01
It needs about 828 GB of VRAM. The cheapest setup that runs it is 8x H200 (1128 GB), from $32.64 per hour, billed per second.
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve deepseek-ai/DeepSeek-V3.2:
vllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does DeepSeek-V3.2 need?
About 689.5 GB for the released FP8 weights, so plan on 828 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 DeepSeek-V3.2?
8x H200 (1128 GB). On Lium that setup costs from $32.64 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt