>>

Run Hy4-flash on Lium

Tencent · Vision and text · 220.3B parameters · 440.5 GB BF16 weights · released 2026-11-17
It needs about 529 GB of VRAM. The cheapest setup that runs it is 8x RTX PRO 6000 Workstation (768 GB), from $12.80 per hour, billed per second.

Other GPUs that run it

4x H200564 GBfrom $17.40 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve tencent/Hy4-flash:
vllm serve tencent/Hy4-flash --tensor-parallel-size 8
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does Hy4-flash need?

About 440.5 GB for the released BF16 weights, so plan on 529 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 Hy4-flash?

8x RTX PRO 6000 Workstation (768 GB). On Lium that setup costs from $12.80 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt