Mistral NeMo is a 12B SLM that excels in reasoning, world knowledge, and coding accuracy. It offers a large context window and is trained with quantization awareness, enabling efficient inference without performance loss.

Some other noteworthy features of Mistral NeMo include multilingual capabilities and function calling support.

Metric	Value
Parameter Count	12 billion
Mixture of Experts	No
Context Length	128,000 tokens
Multilingual	Yes
Quantized*	Yes
Quantization*	FP8

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