>>

Run LFM2.5-8B-A1B on Lium

Liquid AI · Text generation · 8.5B parameters · 16.9 GB BF16 weights · released 2026-05-28
It needs about 21 GB of VRAM. The cheapest setup that runs it is RTX 3090 (24 GB), from $0.19 per hour, billed per second.
Rent RTX 3090

Other GPUs that run it

RTX A600048 GBfrom $0.40 / hourRent
H100 PCIe80 GBfrom $1.79 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve LiquidAI/LFM2.5-8B-A1B:
vllm serve LiquidAI/LFM2.5-8B-A1B
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does LFM2.5-8B-A1B need?

About 16.9 GB for the released BF16 weights, so plan on 21 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 LFM2.5-8B-A1B?

RTX 3090 (24 GB). On Lium that setup costs from $0.19 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt