>>

Run Rubicon-Preview on Lium

Ant Group · Text generation · 30.5B parameters · 61.1 GB BF16 weights · released 2025-08-18
It needs about 74 GB of VRAM. The cheapest setup that runs it is A100 80GB PCIe (80 GB), from $0.81 per hour, billed per second.
Rent A100 80GB PCIe

Other GPUs that run it

2x RTX A600096 GBfrom $0.84 / hourRent
4x RTX 309096 GBfrom $1.16 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve inclusionAI/Rubicon-Preview:
vllm serve inclusionAI/Rubicon-Preview
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does Rubicon-Preview need?

About 61.1 GB for the released BF16 weights, so plan on 74 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 Rubicon-Preview?

A100 80GB PCIe (80 GB). On Lium that setup costs from $0.81 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt