>>
Run Qianfan-VL-70B on Lium
Baidu · Vision and text · 71.8B parameters · 143.7 GB BF16 weights · released 2025-09-16
It needs about 173 GB of VRAM. The cheapest setup that runs it is 4x L40 (192 GB), from $1.32 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 baidu/Qianfan-VL-70B:
vllm serve baidu/Qianfan-VL-70B --tensor-parallel-size 4Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does Qianfan-VL-70B need?
About 143.7 GB for the released BF16 weights, so plan on 173 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 Qianfan-VL-70B?
4x L40 (192 GB). On Lium that setup costs from $1.32 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt