Llama 3.2 3B Instruct is Meta's language model with a 131K context window and up to 80K output tokens, available from 9 providers, starting at $0.015 / 1M input and $0.020 / 1M output. Meta's 3B instruction-tuned LLM from Llama 3.2, providing efficient instruction-following for resource-constrained environments across multiple cloud regions.
Specifications
Canonical IDmeta-llama-3-2-3b-instruct
TypeLanguage
StatusDeprecated
CreatorMetaMeta
Providers
Context Window131K tokens
Max Output80K tokens
Input ModalitiesText
Output ModalitiesText
Parameters3B
HuggingFace Likes2,113
HuggingFace Downloads (30d)1,988,470
HuggingFace Downloads (all-time)40,170,042
Release Date · 2 years ago
Knowledge Cutoff
Deprecation Date
Benchmarks
Intelligence Index
9.7
#400
Math Index
3.3
#248
MMLU-Pro
0.3
#308
GPQA
0.3
#437
HLE
0.1
#261
LiveCodeBench
0.1
#303
AIME
0.1
#132
IFBench
0.3
#353
Time to First Token
0.64s
#280
SciCode
0.1
#418
MATH-500
0.5
#156
AIME 2025
0.0
#248
LCR
0.0
#324
TAU2
0.2
#294
Output TPS
52.1
#214

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.100$0.200Available
Llama 3.2 3B Instruct131K$0.015$0.020Current
Llama 3.2 1B Instruct131K$0.027$0.080Deprecated
Llama 3.1 405B Instruct131K$0.120$0.300Deprecating
Llama 3.1 70B Instruct131K$0.100$0.100Available
Llama 3.1 8B Instruct200K$0.020$0.030Available
Llama 3.1 70B128K$0.600$0.600Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Available
Llama 3 8B Instruct32K$0.030$0.040Available
Llama 3.1 Tulu3 405BAvailable

Model IDs