Run Qwen3.8-27B-DSpine-b16 on Lium

Tencent · Text generation · 2B parameters · 4.1 GB BF16 weights · released 2026-11-07

It needs about 5 GB of VRAM. The cheapest setup that runs it is GTX 1660 Ti (6 GB), from $0.08 per hour, billed per second.

Rent GTX 1660 Ti

Other GPUs that run it

RTX A4500	20 GB	from $0.20 / hour	Rent
T4	16 GB	from $0.22 / hour	Rent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve tencent/Qwen3.8-27B-DSpine-b16:

vllm serve tencent/Qwen3.8-27B-DSpine-b16

Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does Qwen3.8-27B-DSpine-b16 need?

About 4.1 GB for the released BF16 weights, so plan on 5 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-DSpine-b16?

GTX 1660 Ti (6 GB). On Lium that setup costs from $0.08 per hour, billed per second with no minimum.

All open models

For AI agents (CLI install, agent skill, headless signup): llms-full.txt