Run Ling-3.0-tiny on Lium

Ant Group · Text generation · 7.9B parameters · 15.8 GB BF16 weights · released 2026-08-10

It needs about 19 GB of VRAM. The cheapest setup that runs it is RTX A4500 (20 GB), from $0.16 per hour, billed per second.

Rent RTX A4500

Other GPUs that run it

RTX 3090	24 GB	from $0.19 / hour	Rent
2x Tesla V100	32 GB	from $0.42 / hour	Rent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve inclusionAI/Ling-3.0-tiny:

vllm serve inclusionAI/Ling-3.0-tiny

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

Frequently asked questions

How much VRAM does Ling-3.0-tiny need?

About 15.8 GB for the released BF16 weights, so plan on 19 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 Ling-3.0-tiny?

RTX A4500 (20 GB). On Lium that setup costs from $0.16 per hour, billed per second with no minimum.

All open models

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