LiquidAI

LFM3 1.7B

1.7B-parameter edge model post-trained for agentic work, with a 256K-token context window.text generationother78.8K downloadsHugging Face

Cheapest GPU in stock that fits

A single GPU with at least 3.9 GB for inference.

NosanaIn stock · 6 freeStart right away

Nosana network, hosts worldwide

Details

Stock and price checked 15 min ago.

Self-service: you start it yourself, with no order or sales contact.

nvidia-3060

Full price

€0.04

per hour, whole instance, 1 GPU

Commercial use is licensed only below USD 10M annual revenue.

From model cards and vendor documentation. Lower precision needs less memory, with slightly lower quality. Estimates are marked.

What you want to do	Precision	Minimum	Setup	Basis
Run the model Model card: about 1 GB of memory at 4-bit precision. Card says memory, not specifically VRAM.	4-bit	1 GB	Phone or laptop class device (per model card)	Published
Run the model Arithmetic: 3.22 GiB BF16 weights (1.73B parameters x 2 bytes) x 1.2 runtime overhead.	BF16, full	3.9 GB	—	Estimated