>>

Run NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB on Lium

NVIDIA · Vision and text · 24.6B parameters · 24.1 GB 8-bit weights · released 2026-10-07
It needs about 29 GB of VRAM. The cheapest setup that runs it is 2x RTX 3090 (48 GB), from $0.40 per hour, billed per second.
Rent 2x RTX 3090

Other GPUs that run it

RTX A600048 GBfrom $0.42 / hourRent
H100 PCIe80 GBfrom $1.40 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB:
vllm serve nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB --tensor-parallel-size 2
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB need?

About 24.1 GB for the released 8-bit weights, so plan on 29 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 NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB?

2x RTX 3090 (48 GB). On Lium that setup costs from $0.40 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt