Pixtral 12B is a Multimodal LLM designed for processing and understanding both images and text. It excels in tasks such as image captioning, visual question answering, and analyzing complex visual data like graphs, diagrams, and charts.

Some other noteworthy features of Pixtral 12B include its ability to handle multiple images simultaneously and its proficiency in document question answering tasks.

Metric	Value
Parameter Count	12 billion
Mixture of Experts	No
Context Length	128,000 tokens
Multilingual	Yes
Quantized*	Unknown

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.