Megatron MarketsWholesale
Sign inContact Us
Models Model details

Meta Llama

Meta: Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instruct

Enquire about this model Request a quote

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.

Input
$0.05

/ 1M tokens

Output
$0.08

/ 1M tokens

Context window
131.07K

tokens

Limits

Context

131,072

tokens

Max output

117,964

90% of the context window

Parameters

8,030,261,248

Model facts

Author

Meta Llama

Tokenizer

Llama3

Modality

Text -> Text

Instruction format

Llama3

License

Llama3.1

Knowledge cutoff

2023-12-31

Created

Jul 23, 2024

Hugging Face

meta-llama/Meta-Llama-3.1-8B-Instruct

Publication status

Hugging Face: verifiedLicense: publishedParameter count: published

Modalities

Input · TextOutput · Text

Generation controls

Frequency penaltyLogit biasLogprobsMax tokensMin pPresence penaltyRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p

Capability scores

5.4
Coding index

Better than 1% of models compared

6.9
Intelligence index

Better than 9% of models compared