>>
Run deepseek-vl2-tiny on Lium
DeepSeek · Vision and text · 3.4B parameters · 6.7 GB BF16 weights · released 2024-12-13
It needs about 9 GB of VRAM. The cheapest setup that runs it is RTX 3060 (12 GB), from $0.09 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 deepseek-ai/deepseek-vl2-tiny:
vllm serve deepseek-ai/deepseek-vl2-tinyClaude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does deepseek-vl2-tiny need?
About 6.7 GB for the released BF16 weights, so plan on 9 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-vl2-tiny?
RTX 3060 (12 GB). On Lium that setup costs from $0.09 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt