>>
Run Qwen3.8-27B on Lium
Alibaba Qwen · Vision and text · 27.8B parameters · 55.6 GB BF16 weights · released 2026-08-05
It needs about 67 GB of VRAM. The cheapest setup that runs it is 2x L40 (96 GB), from $0.66 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 Qwen/Qwen3.8-27B:
vllm serve Qwen/Qwen3.8-27B --tensor-parallel-size 2Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does Qwen3.8-27B need?
About 55.6 GB for the released BF16 weights, so plan on 67 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 Qwen3.8-27B?
2x L40 (96 GB). On Lium that setup costs from $0.66 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt