GeekRadar / The comparison desk

COMPARE.

AI models

meta

Llama-2-70b

AI model Released Jul 18, 2023

Open weights: Yes

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Llama-2-70b 113.7^* Llama 2-70B · 95% interval 106.1–117.7

Run it locally

Inference · memory estimate

Llama-2-70b

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Open weights: Yes
Model license: llama2

Input modalities

text

Output modalities

text

* Provisional data