>>

Run LFM3-Omni-2B on Lium

Liquid AI · Multimodal · 2.2B parameters · 4.3 GB BF16 weights · released 2026-10-21
It needs about 6 GB of VRAM. The cheapest setup that runs it is RTX A4500 (20 GB), from $0.16 per hour, billed per second.
Rent RTX A4500

Other GPUs that run it

RTX 5060 Ti16 GBfrom $0.17 / hourRent
Tesla V10016 GBfrom $0.21 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve LiquidAI/LFM3-Omni-2B:
vllm serve LiquidAI/LFM3-Omni-2B
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does LFM3-Omni-2B need?

About 4.3 GB for the released BF16 weights, so plan on 6 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 LFM3-Omni-2B?

RTX A4500 (20 GB). On Lium that setup costs from $0.16 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt