Energy per query

1.1 Wh

CO2 per query

0.44 g

Water per query

2 mL

Processing location

Self-hosted (varies)

Provider

Meta

Category

Text / Chat

Grid carbon intensity

475 g CO2/kWh (27% renewable)

How does LLaMA 3.1 70B compare?

00.30.60.91.2LLaMA 3.2 1BGemini 1.5 ProGPT-4.1 NanoLLaMA 3.1 70B

Detailed Breakdown

Energy Consumption

LLaMA 3.1 70B consumes approximately 1.1 Wh per query. At 70 billion parameters, it strikes a balance between capability and efficiency. As an open-source model, it is widely deployed on diverse hardware — the actual energy per query varies significantly based on the GPU type and hosting environment.

Power Source & Carbon

As an open-source model, LLaMA 3.1 70B is self-hosted across diverse infrastructure. The carbon impact depends entirely on where it runs. Meta's own data centers run about 60% on renewable energy.

Water Usage

At approximately 2.1 mL per query, LLaMA 3.1 70B has a modest water footprint when run in a data center. When self-hosted on personal hardware, water consumption for cooling drops to effectively zero.

What does your LLaMA 3.1 70B usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use LLaMA 3.1 70B.

Calculate My Compute

Frequently Asked Questions

How much energy does LLaMA 3.1 70B use per query?

Each LLaMA 3.1 70B query consumes approximately 1.1 Wh of energy. This is 4x more than a traditional Google search (~0.3 Wh).

What is LLaMA 3.1 70B's carbon footprint?

Based on the carbon intensity of Self-hosted (varies), each query produces approximately 0.44 g of CO2. The grid in this region has a carbon intensity of 475 g CO2/kWh with 27% renewable energy.

How much water does LLaMA 3.1 70B use?

Each query consumes approximately 2 mL of water, primarily used for cooling the data centers that process the request.

How does LLaMA 3.1 70B compare to a Google search?

A LLaMA 3.1 70B query uses 4x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while LLaMA 3.1 70B uses 1.1 Wh.

Technical Details

Architecture

Dense Transformer (decoder-only)

Parameters

70B

Context window

128,000 tokens

Release date

2024-07-23

Open source

Yes