Skip to main content

Llama 3.2 Instruct 11B (Vision)

MetaLlamaOpen WeightLlama 3.2 Community License

Description

Llama 3.2 11B Vision Instruct is an instruction-tuned multimodal large language model optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. It accepts text and images as input and generates text as output.

Release Date
2024-09-25
Parameters
10.6B
Context Length
—
Modalities
image, text

Capability Radar

60
general
0
coding
60
reasoning
26
scienceest.
42
agents
90
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

Domain#RankScoreSource
Multimodal Ranking100
44.0
LS

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

General

MMLU73.0%SR

Math

MGSM68.9%SR
MATH51.9%SR
MathVista51.5%SR

Multimodal

MMMU50.7%SR

Reasoning

ChartQAMasry et al. (2022)83.4%SR
GPQANYU + Cohere + Anthropic (2023)32.8%SR

Vision

AI2D91.1%SR
DocVQADocVQA (2020)88.4%SR
VQAv2 (test)75.2%SR
MMMU-Pro33.0%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Image To Text
90
Language
70
Legal
70
Multimodal
70
Finance
70
Vision
70
Math
60
Reasoning
60
General
60
Healthcare
60
Physics
30
Biology
30
Chemistry
30

Pricing

Input Price$0.345 / 1M tokens
Output Price$0.345 / 1M tokens

Speed

Tokens/sec25.4
Time to First Token1.31s
Time to Answer1.31s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1MetaPRIMARY
$0.345
$0.345

Compare pricing across different API providers for this model.

External Sources