Falcon Models — Hardware Requirements

13 Falcon models from TII UAE and the community, from the smallest that runs in 0.0 GB of VRAM up to 41.8B parameters. Every row links to full quantization tables and GPU compatibility.

All Falcon Models by Size

ModelParamsContext
Falcon Mamba Tiny Dev9M—
Falcon H1 Tiny 90M Instruct91M262K
Falcon H1 0.5B Base521M16K
Falcon H1 0.5B Instruct521M16K
Falcon 7B7.2B—
Falcon 7B Instruct7.2B—
Falcon Mamba 7B7.3B—
Falcon3 Mamba 7B Base7.3B—
Falcon H1 7B Base7.6B262K
Falcon H1 7B Instruct7.6B262K
Falcon 11B11.1B8K
Falcon 40B Instruct40B—
Falcon 40B41.8B—

Frequently Asked Questions

How much VRAM do I need to run a Falcon model?
The smallest Falcon model, Falcon Mamba Tiny Dev, runs from 0.0 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which Falcon models can I run on a 16 GB GPU?
12 of 13 Falcon models fit in 16 GB of VRAM at some quantization, including Falcon 40B Instruct, Falcon H1 7B Instruct, Falcon 11B.
What is the most popular Falcon model to run locally?
Falcon 40B Instruct is the most downloaded Falcon model in local-friendly quantized formats. It runs from 12.1 GB of VRAM.
Falcon Models — VRAM & Hardware Requirements | llmrun