>>
Run Llama-4-Maverick-17B-128E-Instruct on Lium
Meta · Vision and text · 401.6B parameters · 803.2 GB BF16 weights · released 2025-04-01
It needs about 964 GB of VRAM. The cheapest setup that runs it is 8x H200 (1128 GB), from $32.00 per hour, billed per second.
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve meta-llama/Llama-4-Maverick-17B-128E-Instruct:
vllm serve meta-llama/Llama-4-Maverick-17B-128E-Instruct --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does Llama-4-Maverick-17B-128E-Instruct need?
About 803.2 GB for the released BF16 weights, so plan on 964 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 Llama-4-Maverick-17B-128E-Instruct?
8x H200 (1128 GB). On Lium that setup costs from $32.00 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt