GeekRadar / The comparison desk

COMPARE.

AI models

meta

LLaMA-7B

AI model Released Feb 24, 2023

Open weights: Yes^*

Capability & preference

General capability · ECI

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

LLaMA-7B 77.9^* LLaMA-7B · 95% interval 63.9–89.6

Run it locally

Inference · memory estimate

LLaMA-7B

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Open weights: Yes^*

System configuration

Detailed specifications

Specifications · 4 fields

Access model: Open weights (non-commercial)^*
Open weights: Yes^*
Organization: Meta AI^*
Organization country: United States of America^*

* Provisional data