microsoft/Phi-3-mini-128k-instruct

The Microsoft Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, instruction-tuned causal language model from the Phi-3 family, developed by Microsoft. It is notable for its extended 128K token context length and robust performance in reasoning, mathematics, and coding benchmarks, particularly among models under 13 billion parameters. This model is optimized for memory/compute-constrained environments and latency-bound scenarios, making it suitable for applications requiring strong reasoning capabilities within resource limitations.