Phi-3-mini
A small language model developed by Microsoft with approximately 3.8 billion parameters. Trained on high-quality data, it achieves performance on certain tasks comparable to larger-scale models. The model supports local deployment, making it suitable for resource-constrained environments.
Timeline (last 90 days)
Small models of the same scale such as Phi-3-mini, Gemma-2B, and Qwen1.5-1.8B, after training on high-quality data, can achieve performance close to larger models on specific tasks.
A 4B parameter model (such as Phi-3-mini or Llama 3.2 3B) requires only approximately 8GB of VRAM and can run on a consumer-grade GPU.
All Facts (3)
A 4B parameter model (such as Phi-3-mini or Llama 3.2 3B) requires only approximately 8GB of VRAM and can run on a consumer-grade GPU.
60%UnverifiedMicrosoft's Phi-3-mini (3.8B parameters) surpassed earlier 7B–13B models on multiple benchmark tests.
60%UnverifiedSmall models of the same scale such as Phi-3-mini, Gemma-2B, and Qwen1.5-1.8B, after training on high-quality data, can achieve performance close to larger models on specific tasks.
50%