>>

Run CogView3-Plus-3B on Lium

Z.ai · Image generation · 2.8B parameters · 25.6 GB BF16 weights · released 2024-10-04
It needs about 31 GB of VRAM. The cheapest setup that runs it is 2x RTX 3090 (48 GB), from $0.38 per hour, billed per second.
Rent 2x RTX 3090

Other GPUs that run it

RTX A600048 GBfrom $0.40 / hourRent
H100 80GB HBM380 GBfrom $2.50 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve zai-org/CogView3-Plus-3B:
vllm serve zai-org/CogView3-Plus-3B --tensor-parallel-size 2
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does CogView3-Plus-3B need?

About 25.6 GB for the released BF16 weights, so plan on 31 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 CogView3-Plus-3B?

2x RTX 3090 (48 GB). On Lium that setup costs from $0.38 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt