Mistral Large 2 is an LLM with 123 billion parameters, designed for high-throughput and long-context applications. It excels in reasoning, coding, and instruction following.

Metric	Value
Parameter Count	123 billion
Mixture of Experts	No
Context Length	128,000 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.