Llama 3.1 Instruct 8B

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Llama 3.1 Instruct 8B by Meta: Text model; TTFT 0.464s, 183.3 tok/s.

Input Modality

Output Modality

Inference Speed

183.338 tokens/s

Latest Release Date

7/23/2024

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Llama 3.1 Instruct 8B

Release date

7/23/2024

Performance

183.338 tokens/s

model_creator.name

Meta

AA Evaluation Scores

AA Intelligence Index

11.8

AA Coding Index

4.9

AA Math Index

4.3

MMLU Pro

0.476

GPQA

0.259

HLE

0.051

LiveCodeBench

0.116

SciCode

0.132

Math-500

0.519

AIME

0.077

AIME 2025

0.043

IFBench

0.286

LCR

0.157

TerminalBench Hard

0.008

TAU2

0.164

Output Speed (tokens/s)

183.338 tok/s

TTFT (s)

0.464s

First Answer Token (s)

0.464s