- Home
- Open models
- ERNIE-4.5-21B-A3B-Thinking
>>
Run ERNIE-4.5-21B-A3B-Thinking on Lium
Baidu · Text generation · 21.8B parameters · 43.7 GB BF16 weights · released 2025-09-08
It needs about 53 GB of VRAM. The cheapest setup that runs it is 4x RTX 3090 (96 GB), from $0.80 per hour, billed per second.
Other GPUs that run it
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve baidu/ERNIE-4.5-21B-A3B-Thinking:
vllm serve baidu/ERNIE-4.5-21B-A3B-Thinking --tensor-parallel-size 4Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does ERNIE-4.5-21B-A3B-Thinking need?
About 43.7 GB for the released BF16 weights, so plan on 53 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 ERNIE-4.5-21B-A3B-Thinking?
4x RTX 3090 (96 GB). On Lium that setup costs from $0.80 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt