Llama 3.3 70B Versatile 128k is an LLM served through the inference provider Groq. It excels in multilingual capabilities, handling long-context tasks, and tool use. While it shows strength in grade school math and arithmetic reasoning, it performs less well on middle school math and verbal reasoning tasks.

Metric	Value
Parameter Count	70 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.