llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsLlama 3.2 3B

Meta model product

Llama 3.2 3B

Llama 3.2 3B Instruct is a large language model that supports a context length of 128K tokens and are state-of-the-art in their class for on-device use cases like summarization, instruction following, and rewriting tasks running locally at the edge.

Updated Aug 10, 2026. Default version: Llama 3.2 3B Instruct

Compare
LLMBoard score20.4Llama 3.2 3B Instruct
Coverage60%8 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Llama 3.2 3B Instruct
Released
Sep 25, 2024
Knowledge cutoff
Unknown
Parameters
3.2B
Context window
128K
Max output
128K
Inputs
text
Outputs
text
Open weights
No
License
Llama 3.2 Community License

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Llama 3.2 3B Instruct category scores

Benchmark results

Published benchmark records for the scored version Llama 3.2 3B Instruct.

15 rows
Columns

Show columns

InfiniteBench/En.MC0.611100.0%CAug 7, 2026
InfiniteBench/En.QA0.211100.0%CAug 7, 2026
NIH/Multi-needle0.811100.0%CAug 7, 2026
Open-rewrite0.411100.0%CAug 7, 2026
TLDR9+ (test)0.211100.0%CAug 7, 2026
BFCL v20.74525.0%CAug 7, 2026
Nexus0.3440.0%CAug 7, 2026
ARC-C0.8173451.5%CAug 7, 2026
HellaSwag0.7242711.5%CAug 7, 2026
MGSM0.6273113.3%CAug 7, 2026
GSM8k0.8404817.0%CAug 7, 2026
IFEval0.8566514.1%CAug 7, 2026
MATH0.5607115.7%CAug 7, 2026
MMLU0.6961004.0%CAug 7, 2026
GPQA0.32182336.5%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

48 rows
Columns

Show columns

textgerman2731056.0232N/AAug 6, 2026
text style controlgerman2731110.0232N/AAug 6, 2026
textexpert3021089.4499N/AAug 6, 2026
textindustry medicine and healthcare3061103.6441N/AAug 6, 2026
text style controlexpert3061176.3499N/AAug 6, 2026
textenglish3111179.84,157N/AAug 6, 2026
text style controlindustry medicine and healthcare3111201.8441N/AAug 6, 2026
textindustry mathematical3121128.5980N/AAug 6, 2026
textindustry legal and government3131115.3506N/AAug 6, 2026
texthard prompts english3141142.71,377N/AAug 6, 2026
textmath3161125.91,136N/AAug 6, 2026
text style controlindustry mathematical3161173.8980N/AAug 6, 2026
text style controlmath3181164.91,136N/AAug 6, 2026
text style controlenglish3201224.24,157N/AAug 6, 2026
textmulti turn3221105.11,299N/AAug 6, 2026
text style controlhard prompts english3231208.71,377N/AAug 6, 2026
textlonger query3241100.71,046N/AAug 6, 2026
textindustry entertainment and sports and media3251084.01,149N/AAug 6, 2026
textindustry life and physical and social science3251106.31,355N/AAug 6, 2026
text style controlmulti turn3251148.71,299N/AAug 6, 2026
text style controlindustry entertainment and sports and media3261141.81,149N/AAug 6, 2026
text style controlindustry legal and government3261188.0506N/AAug 6, 2026
texthard prompts3271095.02,216N/AAug 6, 2026
textindustry software and it services3281104.32,165N/AAug 6, 2026
textinstruction following3281089.33,171N/AAug 6, 2026
text style controlcreative writing3281144.31,070N/AAug 6, 2026
textcreative writing3291094.51,070N/AAug 6, 2026
textindustry business and management and financial operations3291073.41,012N/AAug 6, 2026
textoverall3301109.77,936N/AAug 6, 2026
textcoding3301098.21,351N/AAug 6, 2026
text style controlchinese3321128.5721N/AAug 6, 2026
textchinese3331016.3721N/AAug 6, 2026
text style controllonger query3331158.61,046N/AAug 6, 2026
textexclude ties334933.85,442N/AAug 6, 2026
text style controlindustry life and physical and social science3341185.21,355N/AAug 6, 2026
textindustry writing and literature and language3351095.62,118N/AAug 6, 2026
text style controlindustry writing and literature and language3351141.82,118N/AAug 6, 2026
text style controlinstruction following3351145.53,171N/AAug 6, 2026
text style controlindustry business and management and financial operations3371145.91,012N/AAug 6, 2026
text style controloverall3381166.47,936N/AAug 6, 2026
text style controlhard prompts3381167.62,216N/AAug 6, 2026
text style controlexclude ties3411008.85,442N/AAug 6, 2026
text style controlindustry software and it services3431174.12,165N/AAug 6, 2026
textrussian344948.1933N/AAug 6, 2026
text style controlcoding3441176.01,351N/AAug 6, 2026
text style controlrussian3451004.6933N/AAug 6, 2026
text style controlnon english3471087.63,779N/AAug 6, 2026
textnon english3481018.63,779N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.02 input, $0.02 output per 1M via Inference
Tracked offerings
9
9 rows
Columns

Show columns

Nvidiameta/llama-3.2-3b-instructglobalN/AN/A32.8KAug 7, 2026
Inferencemeta/llama-3.2-3b-instructglobal$0.02$0.0216KAug 7, 2026
LLM Gatewayllama-3.2-3b-instructglobal$0.03$0.0532.8KAug 7, 2026
NovitaAImeta-llama/llama-3.2-3b-instructglobal$0.03$0.0532.8KAug 7, 2026
NanoGPTmeta-llama/llama-3.2-3b-instructglobal$0.0306$0.0493131.1KAug 7, 2026
OpenRoutermeta-llama/llama-3.2-3b-instructglobal$0.05$0.33131.1KAug 7, 2026
Cloudflare Workers AI@cf/meta/llama-3.2-3b-instructglobal$0.0509$0.33580KAug 7, 2026
Cloudflare AI Gatewayworkers-ai/@cf/meta/llama-3.2-3b-instructglobal$0.051$0.34128KAug 7, 2026
Pioneermeta-llama/Llama-3.2-3B-Instructglobal$0.10$0.335131.1KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Llama 3.2 3B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Llama 3.2 3B InstructSep 25, 202420.43.2B128K128KNoLlama 3.2 Community License

What is Llama 3.2 3B?

A concise description based on the published model registry.

Llama 3.2 3B Instruct is a large language model that supports a context length of 128K tokens and are state-of-the-art in their class for on-device use cases like summarization, instruction following, and rewriting tasks running locally at the edge.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Llama 3.2 3B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Llama 3.2 3BvsJamba 1.5 MiniLlama 3.2 3BvsIBM Granite 4.0 TinyLlama 3.2 3BvsQwen2.5 Omni 7BLlama 3.2 3BvsGrok 1.5Llama 3.2 3BvsGemma 3n E4BLlama 3.2 3BvsQwen3.5 2B

Models similar to Llama 3.2 3B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#137+9.1
ME

Llama 3.1 8B

Meta

29.5 LLMBoard

DetailsCompare
#133+12.0
ME

Llama 4 Scout

Meta

32.3 LLMBoard

DetailsCompare
#88+28.1
ME

Llama 4 Maverick

Meta

48.5 LLMBoard

DetailsCompare
#77+32.0
ME

Llama 3.1 70B

Meta

52.4 LLMBoard

DetailsCompare
#69+34.2
ME

Llama 3.3 70B

Meta

54.6 LLMBoard

DetailsCompare
#31+49.5
ME

Llama 3.1 405B

Meta

69.9 LLMBoard

DetailsCompare

FAQ

Common questions about Llama 3.2 3B.

When was Llama 3.2 3B released?

Llama 3.2 3B's default version was released on Sep 25, 2024.

How much does Llama 3.2 3B cost?

No official standard PAYG price is currently available for Llama 3.2 3B. The lowest tracked third-party offer starts at $0.02 input and $0.02 output via Inference.

Who created Llama 3.2 3B?

Llama 3.2 3B is published under Meta in the model registry.

What is the context window for Llama 3.2 3B?

The default version has a 128K token context window.

Is Llama 3.2 3B open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Llama 3.2 3B?

9 published provider offerings are linked to the default version.

What models should I compare Llama 3.2 3B with?

Nearby ranked alternatives include Jamba 1.5 Mini, IBM Granite 4.0 Tiny, Qwen2.5 Omni 7B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai