Llama 3.1 Instruct Turbo (8B)

Model

Release Date: Jul 23, 2024

Developer Meta 🇺🇸

Context Window 131k

Max Output Tokens 4k

Token Costs (in/out) $0.18/0.18

Weights Open

Input Modalities

Accuracy

32.34 %

Avg. Cost (In/Out)

$ 0.18 / $ 0.18

Latency

2.46 s

BenchmarksAccuracyRankings

0.0%

±0.92

140/141

Proprietary BenchmarksAcademic BenchmarksIndustry Partners

View Hyperparameter Settings

Default Provider : Meta

Temperature: Default

Top P: Default

Top K: Default

Max Output Tokens: 4,096