Skip to main content
Meta·current

Llama 3.2 11B Vision

Meta's lightweight open multimodal model — vision + text at 11B parameters

ProviderMeta
Released2024-09-25
StatusCurrent
Context window131K tokens
PricingOpen
Capabilities
textvisioncode
Hugging FaceView on HF ↗

Benchmarks

MMLU (knowledge)73.0

As of 2025-01-01. Source

Loading…

Compare with similar models

Llama 3.2 11B VisionMistral Small 3Llama 3.3 70BDeepSeek V3
Context131K33K131K66K
MMLU73.081.086.088.5
HumanEval91.6
MATH77.090.2
GPQA
PricingOpenOpenOpenOpen
Input $/M$0.10$0.27

Compare more models →