AI Hub
All models
LLMOpen weights

Llama 3.2 3B Instruct

Meta

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
LLM
Access
Open weights
Released
September 25, 2024
License
llama_3_2_community_license
Context window
131,072 tokens
Knowledge cutoff
December 31, 2023
Output speed
172 tok/s
Latency (TTFT)
0.24s
Input
Text
Output
Text
API pricing
$0.05 in · $0.34 out / 1M tokens
Capabilities
Function callingStructured output

Benchmarks

Reasoning

Coding

Math

Compare Llama 3.2 3B Instruct with

See all Llama 3.2 3B Instruct alternatives →