Llama-3.1-70B

AI model Released Jul 23, 2024

Open weights: Yes

Capability & preference

General capability · ECI

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

Llama-3.1-70B 125.9^* Llama 3.1-70B · 95% interval 120.8–128.2

Run it locally

Inference · memory estimate

Llama-3.1-70B

131.4 GiB checkpoint tensor payload · 70.55 B stored tensor elements · BF16

Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.

Capabilities

Open weights: Yes
Model license: llama3.1
Checkpoint tensor payload: 131.42 GiB

Input modalities

text

Output modalities

text

* Provisional data