Skip to main content
AITier

Llama 3.2 Instruct 3B

MetaLlamaOpen WeightLlama 3.2 Community License

Description

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.

Release Date
2024-09-25
Parameters
3.2B
Context Length
131K
Modalities
text

Capability Radar

17
general
8
coding
13
reasoning
14
scienceest.
50
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking450
6.0
AA
General Ranking440
19.0
AA
Math Reasoning332
12.0
AA
Reasoning45
70.0
LS
Science466
12.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA32.8%SR

Finance

MMLU63.4%SR

General

ARC-C78.6%SR
IFEval77.4%SR
BFCL v267.0%SR
Nexus34.3%SR

Language

Open-rewrite40.1%SR
TLDR9+ (test)19.0%SR

Long Context

NIH/Multi-needle84.7%SR
InfiniteBench/En.MC63.3%SR
InfiniteBench/En.QA19.8%SR

Math

GSM8k77.7%SR
MGSM58.2%SR
MATH48.0%SR

Reasoning

HellaSwag69.8%SR

AA Evaluation Indices

Intelligence Index
9.7
Math Index
3.3
Math 500
0.5
Mmlu Pro
0.3
Ifbench
0.3
Gpqa
0.3
Tau2
0.2
Livecodebench
0.1
Aime
0.1
Hle
0.1
Scicode
0.1
Aime 25
0.0
Lcr
0.0

LLM Stats Category Scores

Structured Output
80
Instruction Following
80
Finance
60
General
60
Healthcare
60
Language
60
Legal
60
Math
60
Reasoning
60
Tool Calling
50
Biology
30
Chemistry
30
Physics
30

Pricing

Input Price$0.15 / 1M tokens
Output Price$0.15 / 1M tokens
Blended Price (3:1)$0.15 / 1M tokens

Speed

Tokens/sec52.1 tokens/s
Time to First Token0.68s
Time to Answer0.68s

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats