Mistral Small is an LLM designed for low-latency workloads. It excels in retrieval-augmented generation (RAG), coding tasks, and multilingual support.

Some noteworthy features of Mistral Small include its ability to handle long context windows up to 32,000 tokens and its strong performance in multiple languages such as French, German, Spanish, Italian, and English.

Metric	Value
Parameter Count	24 billion
Mixture of Experts	No
Context Length	32,000 tokens
Multilingual	Yes
Quantized*	No

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