Llama 3.2 Instruct 1B

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Llama 3.2 Instruct 1B by Meta: Text model; TTFT 0.603s, 147.3 tok/s.

Input Modality

Output Modality

Inference Speed

147.316 tokens/s

Latest Release Date

9/25/2024

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Llama 3.2 Instruct 1B

Release date

9/25/2024

Performance

147.316 tokens/s

model_creator.name

Meta

AA Evaluation Scores

AA Intelligence Index

6.3

AA Coding Index

0.6

AA Math Index

MMLU Pro

0.2

GPQA

0.196

HLE

0.053

LiveCodeBench

0.019

SciCode

0.017

Math-500

0.14

AIME

AIME 2025

IFBench

0.228

LCR

0.05

TerminalBench Hard

TAU2

Output Speed (tokens/s)

147.316 tok/s

TTFT (s)

0.603s

First Answer Token (s)

0.603s